# arcjet-js - Doramagic AI Context Pack

> Positioning: a pre-install experience and judgment asset. It helps the host AI get off to a good start, but it does not mean the project has already been installed, run, or validated.

## Sufficiency Principle

- **Sufficiency over compression**: The AI Context Pack should be sufficient for the host AI to understand the project's value, capability boundaries, entrypoints, risks, and evidence sources before starting work; it may be layered, but it does not aim for the shortest possible summary.
- **Compression policy**: Compress only noise and duplication, never context that affects judgment or the quality of the work.

## How the Host AI Should Use This

You are reading the AI Context Pack that Doramagic compiled for arcjet-js. Treat it as pre-work context: help the user understand who it fits, what it can do, how to start, what must be verified after install, and where the risks are. Do not claim that you have already installed, run, or executed the target project.

## Claim Consumption Rules

- **Fact source**: Repo Evidence + Claim/Evidence Graph; the Human Wiki only supplies salience, terminology, and narrative structure.
- **Minimum status for a fact**: `supported`
- `supported`: May be used as a project fact, but the answer must cite the claim_id and evidence path.
- `weak`: Usable only as a low-confidence lead; the user must be asked to keep verifying.
- `inferred`: Usable only for risk notes or open questions; must not be packaged as a project fact.
- `unverified`: Must not be used as fact; state clearly that evidence is insufficient.
- `contradicted`: Must show the conflicting sources and must not force a single version on the user's behalf.

## Who It Fits Best

- **Developers already using host AIs such as Claude/Codex/Cursor/Gemini**: The README or plugin config mentions multiple host AIs. Evidence: `README.md` Claim: `clm_0002` supported 0.86

## What It Can Do

- **Command-Line Startup or Install Flow** (Verify after install): The project documentation contains runnable commands; real use requires running them in a local or host environment. Evidence: `README.md` Claim: `clm_0001` supported 0.86

## How to Start

- `npx @arcjet/cli auth login` Evidence: `README.md` Claim: `clm_0003` supported 0.86
- `npx skills add arcjet/skills` Evidence: `README.md` Claim: `clm_0004` supported 0.86
- `npm i @arcjet/guard` Evidence: `README.md` Claim: `clm_0005` supported 0.86

## Continue-or-Stop Decision Card

- **Current recommendation**: Trial role matching first
- **Why**: This project is more of a role library; the core risk is picking the wrong role or treating role copy as execution capability. Trial role matching with Prompt Preview first, then decide whether to sandbox-import it.

### 30-Second Read

- **What to do now**: Trial role matching first
- **Minimum safe next step**: Trial role matching with Prompt Preview first; import in isolation only once satisfied
- **Do not trust yet**: Role quality and task fit cannot be trusted directly.
- **Continuing will touch**: Role selection bias, Command execution, Local environment or project files

### What You Can Trust Now

- **Target-audience signal: Developers already using host AIs such as Claude/Codex/Cursor/Gemini** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `README.md` Claim: `clm_0002` supported 0.86
- **Capability exists: Command-Line Startup or Install Flow** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `README.md` Claim: `clm_0001` supported 0.86
- **There are Quick Start / install-command signals** (supported): You can trust that the docs mention a startup or install entrypoint; do not run it directly in your primary environment because of that. Evidence: `README.md` Claim: `clm_0003` supported 0.86

### What You Cannot Trust Yet

- **Role quality and task fit cannot be trusted directly.** (unverified): A role library proves there are many roles; it does not prove each one fits your specific task or that a role produces high-quality results.
- **Do not treat role copy as real execution capability.** (unverified): Before install you can only judge whether the role description and task profile match; you cannot prove it can complete the task inside the host AI.
- **Real output quality cannot be trusted before install.** (unverified): Prompt Preview can only show how it guides you; it cannot prove result quality in the real project.
- **Host AI version compatibility cannot be trusted before install.** (unverified): Host loading rules and version differences across Claude, Cursor, Codex, Gemini, and others must be verified in a real environment.
- **That it will not pollute your existing host AI's behavior cannot be trusted directly.** (inferred): Skill, plugin, and AGENTS/CLAUDE/GEMINI instructions may change the host AI's default behavior.
- **Safe rollback cannot be assumed by default.** (unverified): Unless the project clearly provides uninstall and recovery instructions, verify in an isolated environment first.
- **After a real install, is it compatible with the user's current host AI version?** (unverified): Compatibility can only be verified in the actual host environment.
- **Does the project's output quality meet the user's specific task?** (unverified): The pre-install preview can only show flow and boundaries; it cannot replace real evaluation.

### What Continuing Will Touch

- **Role selection bias**: The user's judgment about which expert role should handle the task. Why: Picking the wrong role makes the AI answer from the wrong expert perspective, wasting time or misleading decisions.
- **Command execution**: Package managers, network downloads, the local plugin directory, project config, or the user's home directory. Why: Running the very first command can already change your environment; decide whether it is worth running first. Evidence: `README.md`
- **Local environment or project files**: Install results, plugin caches, project config, or local dependency directories. Why: The write scope and rollback path cannot be proven before install and need isolated verification. Evidence: `README.md`
- **Host AI context**: The AI Context Pack, Prompt Preview, Skill routing, risk rules, and project facts. Why: Importing context affects the host AI's later judgment, so avoid packaging unverified items as facts.

### Minimum Safe Next Steps

- **Run Prompt Preview first**: Use an interactive trial to verify the task profile and role match first; do not import the whole role library up front. (applies when: Applies to any project, especially when output quality is unknown.)
- **Trial-install only in an isolated directory or a test account**: Avoid letting install commands pollute your primary host AI, real projects, or home directory. (applies when: When there are signals of command execution, plugin config, or local writes.)
- **After install, verify just one minimal task**: Verify loading, compatibility, output quality, and rollback first, then decide whether to use it deeply. (applies when: When moving from a trial into a real workflow.)

### Exit Plan

- **Preserve the pre-install state**: Record the original host config and project state so you can later judge whether it is recoverable.
- **Keep a record of the original role selection**: If output goes off-topic, you can return to the task-profiling stage and reselect a role instead of pushing on with the wrong one.
- **Record the install commands and written paths**: Without clear uninstall instructions, you at least need to know which directories or configs to clean up manually.
- **If there is no rollback path, do not enter your primary environment**: No rollback is a blocker before continuing; do not proceed on trust or luck.

## What Can Only Be Previewed

- Explain who the project fits and what it can do
- Demonstrate a typical conversation flow based on project docs
- Help the user decide whether it is worth installing or researching further

## What Must Be Verified After Install

- Actually installing the Skill, plugin, or CLI
- Running scripts, modifying local files, or accessing external services
- Verifying real output quality, performance, and compatibility

## Boundary & Risk Decision Card

- **Mistaking the pre-install preview for a real run**: The user may overestimate how much configuration, permission, and compatibility verification the project has already done. Mitigation: Clearly separate prompt_preview_can_do from runtime_required. Claim: `clm_0006` inferred 0.45
- **Command execution will modify the local environment**: Install commands may write to the user's home directory, the host plugin directory, or project configuration. Mitigation: Run in an isolated environment or a test account first. Evidence: `README.md` Claim: `clm_0007` supported 0.86
- **To confirm**: After a real install, is it compatible with the user's current host AI version?. Why: Compatibility can only be verified in the actual host environment.
- **To confirm**: Does the project's output quality meet the user's specific task?. Why: The pre-install preview can only show flow and boundaries; it cannot replace real evaluation.
- **To confirm**: Do the install commands require network access, permissions, or global writes?. Why: This affects install risk in both enterprise and personal environments.

## Pre-Work Working Context

### Loading Order

- First read how_to_use.host_ai_instruction to establish the boundaries of this pre-install judgment asset.
- Read claim_graph_summary to confirm facts come from the Claim/Evidence Graph, not the Human Wiki narrative.
- Then read intended_users, capabilities, and quick_start_candidates to judge whether the user is a match.
- When you need to carry out a concrete task, check role_skill_index first, then evidence_index.
- For real install, file modification, network access, performance, or compatibility questions, turn to risk_card and boundaries.runtime_required.

### Task Routes

- **Command-Line Startup or Install Flow**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `README.md` Claim: `clm_0001` supported 0.86

### Context Scale

- Total files: 867
- Important-file coverage: 40/867
- Evidence index entries: 80
- Role / Skill entries: 62

### Handling Insufficient Evidence

- **missing_evidence**: State that evidence is insufficient and ask the user for the target file, a README section, or after-install verification records; do not fill in facts.
- **out_of_scope_request**: State that the task is beyond the current AI Context Pack's evidence scope and suggest the user check the Human Manual or verify after a real install.
- **runtime_request**: Provide a pre-install checklist and command sources, but do not run commands for the user or claim they have been run.
- **source_conflict**: Show the conflicting sources side by side, mark them as unverified, and do not force a single version.

## Prompt Recipes

### Fit assessment

- Goal: Judge whether this project fits the user's current task.
- Expected output: A fit conclusion, key reasons, evidence citations, what can be previewed before install, what must be verified after install, and a next-step recommendation.

```text
Based on the AI Context Pack for arcjet-js, ask me 3 necessary questions first, then judge whether it fits my task. The answer must cover: who it fits, what it can do, what it cannot do, whether it is worth installing, and where the evidence comes from. Every project fact must cite evidence_refs, source_paths, or a claim_id.
```

### Pre-install experience

- Goal: Let the user feel the core workflow before installing, while avoiding packaging the preview as real capability or a marketing promise.
- Expected output: An experience script with boundary labels, an after-install verification checklist, and a cautious recommendation; with no real-run promises or strong marketing language.

```text
Treat arcjet-js as a pre-install experience asset, not an already-installed tool or a real runtime environment.

Output exactly four parts:
1. Ask me 3 necessary questions first.
2. Give an "experience script": use the three labels [Previewable before install], [Must verify after install], and [Insufficient evidence] to show how it might guide the workflow.
3. Give an after-install verification checklist: list which capabilities can only be confirmed after a real install, real host loading, and a real project run.
4. Give a cautious recommendation: only "worth researching/trialing further", "add information before deciding", or "not recommended to continue"; do not endorse the project.

Hard boundaries:
- Do not claim you have installed, run, executed tests, modified files, or produced real results.
- Do not write promise-like phrasing such as "auto-adapts", "guarantees passing", "perfect fit", or "strongly recommend installing".
- If you describe how it works after install, you must use a conditional such as "if installed successfully and the host loads the Skill correctly, it might...".
- The experience script may only be written as "example lines / hypothetical flow": use "might ask / might suggest / might show", not "has written, has generated, has passed, is running, is generating".
- Prompt Preview does not hand out install commands; if the user is ready to trial, only prompt them to read Quick Start and the Risk Card first and to verify in an isolated environment.
- Every project fact must come from a supported claim, evidence_refs, or source_paths; inferred/unverified items can only be risks or open questions.

```

### Role / Skill selection

- Goal: Pick the best-matching asset from the project's roles or Skills.
- Expected output: A list of candidate roles or Skills, each with an applicable scenario, evidence paths, risk boundary, and whether after-install verification is needed.

```text
Read role_skill_index and recommend 3-5 of the most relevant roles or Skills for my target task. For each recommendation, state the applicable scenario, likely output, risk boundary, and evidence_refs.
```

### Risk pre-check

- Goal: Identify environment, permission, rule-conflict, and quality risks before installing or adopting.
- Expected output: A checklist of environment, permission, dependency, license, host-conflict, quality risk, and unknown items.

```text
Based on risk_card, boundaries, and quick_start_candidates, give me a pre-install risk pre-check list. Do not run commands for me; only explain what I should check, why, and what impact a failure would have.
```

### Host AI kickoff instruction

- Goal: Turn the project context into a host AI instruction for the start of a conversation.
- Expected output: A pre-work instruction with clear boundaries and clear evidence citations, suitable to copy to a host AI.

```text
Based on the AI Context Pack for arcjet-js, generate a pre-work instruction I can paste to my host AI. This instruction must obey not_runtime=true and must not claim the project has been installed, run, or produced real results.
```

## Role / Skill Index

- Indexed 62 role / Skill / project-doc entries.

- **Arcjet - JS SDK** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `README.md`
- **@arcjet/analyze-wasm** (project_doc): Arcjet arcjet helps developers protect their apps in just a few lines of code. Implement rate limiting, bot protection, email verification, and defense against common attacks. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `analyze-wasm/README.md`
- **@arcjet/analyze** (project_doc): Arcjet arcjet helps developers protect their apps in just a few lines of code. Implement rate limiting, bot protection, email verification, and defense against common attacks. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `analyze/README.md`
- **@arcjet/astro** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Astro application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-astro/README.md`
- **@arcjet/bun** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Bun application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-bun/README.md`
- **@arcjet/deno** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Deno application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-deno/README.md`
- **@arcjet/fastify** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Fastify application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-fastify/README.md`
- **@arcjet/guard** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Guards provide rate limiting, prompt injection detection, sensitive information detection, and custom rules for AI tool calls and other backend operations. Every feature works on Node.js, Deno, Bun, and Cloudflare Workers. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-guard/README.md`
- **@arcjet/nest** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any NestJS application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-nest/README.md`
- **@arcjet/next** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Next.js application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-next/README.md`
- **@arcjet/node** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Node.js application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-node/README.md`
- **@arcjet/nuxt** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Nuxt application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-nuxt/README.md`
- **@arcjet/react-router** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any React Router application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-react-router/README.md`
- **@arcjet/remix** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Remix application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-remix/README.md`
- **@arcjet/sveltekit** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any SvelteKit application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet-sveltekit/README.md`
- **arcjet** (project_doc): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `arcjet/README.md`
- **@arcjet/body** (project_doc): Arcjet arcjet utilities for getting the body from a stream. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `body/README.md`
- **@arcjet/cache** (project_doc): Arcjet arcjet cache interface and implementations. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `cache/README.md`
- **@arcjet/decorate** (project_doc): Arcjet arcjet utilities for decorating responses with information. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `decorate/README.md`
- **@arcjet/duration** (project_doc): Arcjet arcjet utilities for parsing duration strings. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `duration/README.md`
- **@arcjet/env** (project_doc): Arcjet arcjet environment detection. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `env/README.md`
- **Arcjet Examples** (project_doc): This directory contains examples of how to use Arcjet. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/README.md`
- **@arcjet/headers** (project_doc): Arcjet arcjet extension of the Headers class. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `headers/README.md`
- **@arcjet/inspect** (project_doc): Arcjet arcjet utilities for inspecting decisions made by an SDK. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `inspect/README.md`
- **@arcjet/ip** (project_doc): Arcjet arcjet utilities for finding the originating IP of a request. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `ip/README.md`
- **@arcjet/logger** (project_doc): Arcjet arcjet lightweight logger which mirrors the Pino pino-api structured logger interface. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `logger/README.md`
- **@nosecone/next** (project_doc): Protect your Next.js application with secure headers. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `nosecone-next/README.md`
- **@nosecone/sveltekit** (project_doc): Protect your SvelteKit application with secure headers. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `nosecone-sveltekit/README.md`
- **nosecone** (project_doc): Protect your Response with secure headers. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `nosecone/README.md`
- **@arcjet/protocol** (project_doc): The TypeScript & JavaScript interface into the Arcjet arcjet protocol. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `protocol/README.md`
- **@arcjet/redact-wasm** (project_doc): Arcjet arcjet sensitive information redaction detection engine. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `redact-wasm/README.md`
- **@arcjet/redact** (project_doc): Arcjet arcjet helps developers protect their apps in just a few lines of code. Implement rate limiting, bot protection, email verification, and defense against common attacks. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `redact/README.md`
- **@arcjet/runtime** (project_doc): This package attempts to discover and provide runtime keys runtime-keys as defined by the WinterCG wintercg . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `runtime/README.md`
- **@arcjet/sensitive-info-rampart** (project_doc): Arcjet arcjet helps developers protect their apps in just a few lines of code. Implement rate limiting, bot protection, email verification, and defense against common attacks. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `sensitive-info-rampart/README.md`
- **@arcjet/sprintf** (project_doc): Arcjet arcjet platform-independent replacement for util.format node-util . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `sprintf/README.md`
- **@arcjet/stable-hash** (project_doc): Arcjet arcjet stable hashing utility. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `stable-hash/README.md`
- **@arcjet/transport** (project_doc): Transport mechanisms for the Arcjet arcjet protocol. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `transport/README.md`
- **Arcjet Integration with Astro** (project_doc): This example shows how to use the Arcjet Integration with astro https://astro.build/ . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/astro/README.md`
- **Arcjet Rate Limit with Bun.sh** (project_doc): This example shows how to use Arcjet with a Bun.sh https://bun.sh/guides/http/server server. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/bun-rate-limit/README.md`
- **Arcjet Sensitive Info Detection with Deno** (project_doc): Arcjet Sensitive Info Detection with Deno Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/deno-sensitive-info/README.md`
- **Arcjet Bot Detection with Express for Node.js** (project_doc): Arcjet Bot Detection with Express for Node.js Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/express-bots/README.md`
- **Testing Arcjet with Express and Newman** (project_doc): Testing Arcjet with Express and Newman Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/express-newman/README.md`
- **Arcjet Rate Limit with Express for Node.js** (project_doc): Arcjet Rate Limit with Express for Node.js Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/express-rate-limit/README.md`
- **Arcjet Sensitive Info Detection with Express for Node.js** (project_doc): Arcjet Sensitive Info Detection with Express for Node.js Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/express-sensitive-info/README.md`
- **Arcjet email verification with Express for Node.js** (project_doc): Arcjet email verification with Express for Node.js Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/express-validate-email/README.md`
- **Arcjet Protection with Fastify** (project_doc): This example shows how to use Arcjet with a Fastify servers. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/fastify/README.md`
- **Arcjet Protection with NestJS** (project_doc): This example shows how to use Arcjet to protect NestJS https://nestjs.com/ applications using the @arcjet/nest adapter. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nestjs/README.md`
- **Arcjet Rate Limit with Next.js using the App Router** (project_doc): Arcjet Rate Limit with Next.js using the App Router Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nextjs-app-dir-rate-limit/README.md`
- **Arcjet email verification with Next.js using the App Router** (project_doc): Arcjet email verification with Next.js using the App Router Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nextjs-app-dir-validate-email/README.md`
- **Arcjet Bot Detection leveraging categories with Next.js** (project_doc): Arcjet Bot Detection leveraging categories with Next.js Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nextjs-bot-categories/README.md`
- **Arcjet response decoration with Next.js** (project_doc): Arcjet response decoration with Next.js Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nextjs-decorate/README.md`
- **Using the ip property on an ArcjetDecision with Next.js** (project_doc): Using the ip property on an ArcjetDecision with Next.js Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nextjs-ip-details/README.md`
- **Using withArcjet with Next.js and the Pages Router** (project_doc): Using withArcjet with Next.js and the Pages Router Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nextjs-pages-wrap/README.md`
- **Protecting a Next.js React Hook Form with Arcjet** (project_doc): Protecting a Next.js React Hook Form with Arcjet Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nextjs-react-hook-form/README.md`
- **Arcjet Block Sensitive Info with Next.js using the App Router** (project_doc): Arcjet Block Sensitive Info with Next.js using the App Router Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nextjs-sensitive-info/README.md`
- **Arcjet email verification with Next.js Server Actions** (project_doc): Arcjet email verification with Next.js Server Actions Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nextjs-server-actions/README.md`
- **Arcjet Rate Limit with Node.js** (project_doc): This example shows how to use Arcjet with a Node.js server. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nodejs-rate-limit/README.md`
- **Arcjet + Nuxt** (project_doc): This example shows how to use Arcjet in a Nuxt https://nuxt.com/ app. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/nuxt/README.md`
- **Arcjet + React Router using middleware** (project_doc): Arcjet + React Router using middleware Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/react-router-middleware/README.md`
- **Arcjet + React Router** (project_doc): This example shows how to use Arcjet in a React Router https://reactrouter.com app. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/react-router/README.md`
- **Arcjet protections with Remix** (project_doc): This example shows how to leverage Arcjet protections in a Remix https://remix.run/ application. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/remix-express/README.md`
- **Arcjet Protection with Svelte** (project_doc): This example shows how to use Arcjet to protect SvelteKit https://kit.svelte.dev/ apps. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `examples/sveltekit/README.md`

## Evidence Index

- Indexed 80 evidence entries.

- **Arcjet - JS SDK** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Evidence: `README.md`
- **@arcjet/analyze-wasm** (documentation): Arcjet arcjet helps developers protect their apps in just a few lines of code. Implement rate limiting, bot protection, email verification, and defense against common attacks. Evidence: `analyze-wasm/README.md`
- **@arcjet/analyze** (documentation): Arcjet arcjet helps developers protect their apps in just a few lines of code. Implement rate limiting, bot protection, email verification, and defense against common attacks. Evidence: `analyze/README.md`
- **@arcjet/astro** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Astro application. Evidence: `arcjet-astro/README.md`
- **@arcjet/bun** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Bun application. Evidence: `arcjet-bun/README.md`
- **@arcjet/deno** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Deno application. Evidence: `arcjet-deno/README.md`
- **@arcjet/fastify** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Fastify application. Evidence: `arcjet-fastify/README.md`
- **@arcjet/guard** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Guards provide rate limiting, prompt injection detection, sensitive information detection, and custom rules for AI tool calls and other backend operations. Every feature works on Node.js, Deno, Bun, and Cloudflare Workers. Evidence: `arcjet-guard/README.md`
- **@arcjet/nest** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any NestJS application. Evidence: `arcjet-nest/README.md`
- **@arcjet/next** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Next.js application. Evidence: `arcjet-next/README.md`
- **@arcjet/node** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Node.js application. Evidence: `arcjet-node/README.md`
- **@arcjet/nuxt** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Nuxt application. Evidence: `arcjet-nuxt/README.md`
- **@arcjet/react-router** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any React Router application. Evidence: `arcjet-react-router/README.md`
- **@arcjet/remix** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any Remix application. Evidence: `arcjet-remix/README.md`
- **@arcjet/sveltekit** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Every feature works with any SvelteKit application. Evidence: `arcjet-sveltekit/README.md`
- **arcjet** (documentation): Arcjet arcjet is the runtime security platform that ships with your AI code. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks. Evidence: `arcjet/README.md`
- **@arcjet/body** (documentation): Arcjet arcjet utilities for getting the body from a stream. Evidence: `body/README.md`
- **@arcjet/cache** (documentation): Arcjet arcjet cache interface and implementations. Evidence: `cache/README.md`
- **@arcjet/decorate** (documentation): Arcjet arcjet utilities for decorating responses with information. Evidence: `decorate/README.md`
- **@arcjet/duration** (documentation): Arcjet arcjet utilities for parsing duration strings. Evidence: `duration/README.md`
- **@arcjet/env** (documentation): Arcjet arcjet environment detection. Evidence: `env/README.md`
- **Arcjet Examples** (documentation): This directory contains examples of how to use Arcjet. Evidence: `examples/README.md`
- **@arcjet/headers** (documentation): Arcjet arcjet extension of the Headers class. Evidence: `headers/README.md`
- **@arcjet/inspect** (documentation): Arcjet arcjet utilities for inspecting decisions made by an SDK. Evidence: `inspect/README.md`
- **@arcjet/ip** (documentation): Arcjet arcjet utilities for finding the originating IP of a request. Evidence: `ip/README.md`
- **@arcjet/logger** (documentation): Arcjet arcjet lightweight logger which mirrors the Pino pino-api structured logger interface. Evidence: `logger/README.md`
- **@nosecone/next** (documentation): Protect your Next.js application with secure headers. Evidence: `nosecone-next/README.md`
- **@nosecone/sveltekit** (documentation): Protect your SvelteKit application with secure headers. Evidence: `nosecone-sveltekit/README.md`
- **nosecone** (documentation): Protect your Response with secure headers. Evidence: `nosecone/README.md`
- **@arcjet/protocol** (documentation): The TypeScript & JavaScript interface into the Arcjet arcjet protocol. Evidence: `protocol/README.md`
- **@arcjet/redact-wasm** (documentation): Arcjet arcjet sensitive information redaction detection engine. Evidence: `redact-wasm/README.md`
- **@arcjet/redact** (documentation): Arcjet arcjet helps developers protect their apps in just a few lines of code. Implement rate limiting, bot protection, email verification, and defense against common attacks. Evidence: `redact/README.md`
- **@arcjet/runtime** (documentation): This package attempts to discover and provide runtime keys runtime-keys as defined by the WinterCG wintercg . Evidence: `runtime/README.md`
- **@arcjet/sensitive-info-rampart** (documentation): Arcjet arcjet helps developers protect their apps in just a few lines of code. Implement rate limiting, bot protection, email verification, and defense against common attacks. Evidence: `sensitive-info-rampart/README.md`
- **@arcjet/sprintf** (documentation): Arcjet arcjet platform-independent replacement for util.format node-util . Evidence: `sprintf/README.md`
- **@arcjet/stable-hash** (documentation): Arcjet arcjet stable hashing utility. Evidence: `stable-hash/README.md`
- **@arcjet/transport** (documentation): Transport mechanisms for the Arcjet arcjet protocol. Evidence: `transport/README.md`
- **Arcjet Integration with Astro** (documentation): This example shows how to use the Arcjet Integration with astro https://astro.build/ . Evidence: `examples/astro/README.md`
- **Arcjet Rate Limit with Bun.sh** (documentation): This example shows how to use Arcjet with a Bun.sh https://bun.sh/guides/http/server server. Evidence: `examples/bun-rate-limit/README.md`
- **Arcjet Sensitive Info Detection with Deno** (documentation): Arcjet Sensitive Info Detection with Deno Evidence: `examples/deno-sensitive-info/README.md`
- **Arcjet Bot Detection with Express for Node.js** (documentation): Arcjet Bot Detection with Express for Node.js Evidence: `examples/express-bots/README.md`
- **Testing Arcjet with Express and Newman** (documentation): Testing Arcjet with Express and Newman Evidence: `examples/express-newman/README.md`
- **Arcjet Rate Limit with Express for Node.js** (documentation): Arcjet Rate Limit with Express for Node.js Evidence: `examples/express-rate-limit/README.md`
- **Arcjet Sensitive Info Detection with Express for Node.js** (documentation): Arcjet Sensitive Info Detection with Express for Node.js Evidence: `examples/express-sensitive-info/README.md`
- **Arcjet email verification with Express for Node.js** (documentation): Arcjet email verification with Express for Node.js Evidence: `examples/express-validate-email/README.md`
- **Arcjet Protection with Fastify** (documentation): This example shows how to use Arcjet with a Fastify servers. Evidence: `examples/fastify/README.md`
- **Arcjet Protection with NestJS** (documentation): This example shows how to use Arcjet to protect NestJS https://nestjs.com/ applications using the @arcjet/nest adapter. Evidence: `examples/nestjs/README.md`
- **Arcjet Rate Limit with Next.js using the App Router** (documentation): Arcjet Rate Limit with Next.js using the App Router Evidence: `examples/nextjs-app-dir-rate-limit/README.md`
- **Arcjet email verification with Next.js using the App Router** (documentation): Arcjet email verification with Next.js using the App Router Evidence: `examples/nextjs-app-dir-validate-email/README.md`
- **Arcjet Bot Detection leveraging categories with Next.js** (documentation): Arcjet Bot Detection leveraging categories with Next.js Evidence: `examples/nextjs-bot-categories/README.md`
- **Arcjet response decoration with Next.js** (documentation): Arcjet response decoration with Next.js Evidence: `examples/nextjs-decorate/README.md`
- **Using the ip property on an ArcjetDecision with Next.js** (documentation): Using the ip property on an ArcjetDecision with Next.js Evidence: `examples/nextjs-ip-details/README.md`
- **Using withArcjet with Next.js and the Pages Router** (documentation): Using withArcjet with Next.js and the Pages Router Evidence: `examples/nextjs-pages-wrap/README.md`
- **Protecting a Next.js React Hook Form with Arcjet** (documentation): Protecting a Next.js React Hook Form with Arcjet Evidence: `examples/nextjs-react-hook-form/README.md`
- **Arcjet Block Sensitive Info with Next.js using the App Router** (documentation): Arcjet Block Sensitive Info with Next.js using the App Router Evidence: `examples/nextjs-sensitive-info/README.md`
- **Arcjet email verification with Next.js Server Actions** (documentation): Arcjet email verification with Next.js Server Actions Evidence: `examples/nextjs-server-actions/README.md`
- **Arcjet Rate Limit with Node.js** (documentation): This example shows how to use Arcjet with a Node.js server. Evidence: `examples/nodejs-rate-limit/README.md`
- **Arcjet + Nuxt** (documentation): This example shows how to use Arcjet in a Nuxt https://nuxt.com/ app. Evidence: `examples/nuxt/README.md`
- **Arcjet + React Router using middleware** (documentation): Arcjet + React Router using middleware Evidence: `examples/react-router-middleware/README.md`
- **Arcjet + React Router** (documentation): This example shows how to use Arcjet in a React Router https://reactrouter.com app. Evidence: `examples/react-router/README.md`
- The remaining 20 evidence entries are in `AI_CONTEXT_PACK.json` or `EVIDENCE_INDEX.json`.

## Rules the Host AI Must Follow

- **Treat this asset as pre-work context, not a runtime environment.**: The AI Context Pack contains only an evidence-backed understanding of the project, not the project's executable state. Evidence: `README.md`, `analyze-wasm/README.md`, `analyze/README.md`
- **When answering the user, distinguish what can be previewed from what can only be verified after install.**: The consumer value of the pre-install experience comes from reducing bad installs and misjudgments, not from pretending to be a real run. Evidence: `README.md`, `analyze-wasm/README.md`, `analyze/README.md`

## Questions the User Should Answer First

- Which host AI or local environment do you plan to use it in?
- Do you just want to experience the workflow first, or are you ready to actually install?
- What matters most to you: install cost, output quality, or conflicts with your existing rules?

## Acceptance Checks

- Every capability claim can be traced back to a file path in evidence_refs.
- AI_CONTEXT_PACK.md does not package previews as a real run.
- The user can understand who it fits, what it can do, how to start, and the risk boundaries within 3 minutes.

---

## Doramagic Context Augmentation

The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints.

## Human Manual Outline

Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph.

Host AI hard rules:
- Do not treat page titles, section order, summaries, or importance values as factual project evidence.
- When explaining the Human Manual outline, state that it is only a reading route or salience signal.
- Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph.

- **Getting Started and Package Selection**: importance `high`
  - source_paths: README.md, package.json, CONTRIBUTING.md, CHANGELOG.md
- **Framework SDKs (Request Protection)**: importance `high`
  - source_paths: arcjet/src/index.ts, arcjet-next/src/index.ts, arcjet-node/src/index.ts, arcjet-bun/src/index.ts, arcjet-deno/src/index.ts
- **Arcjet Guard (Non-HTTP Protection)**: importance `high`
  - source_paths: arcjet-guard/src/index.ts, arcjet-guard/src/client.ts, arcjet-guard/src/rules.ts, arcjet-guard/src/convert.ts, arcjet-guard/src/types.ts
- **Core Architecture and Shared Internals**: importance `high`
  - source_paths: protocol/src/index.ts, protocol/src/client.ts, protocol/src/convert.ts, transport/src/index.ts, transport/src/proxy-tunnel.ts

## Repo Inspection Evidence

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `22d48de4760190651fb9fe536594c744a8b7565c`
- inspected_files: `README.md`, `package.json`, `examples/README.md`, `examples/astro/README.md`, `examples/astro/package-lock.json`, `examples/astro/package.json`, `examples/astro/src/actions/index.ts`, `examples/astro/src/env.d.ts`, `examples/astro/src/middleware.ts`, `examples/astro/src/pages/randomizer.json.ts`, `examples/astro/tsconfig.json`, `examples/bun-rate-limit/README.md`, `examples/bun-rate-limit/bunfig.toml`, `examples/bun-rate-limit/index.ts`, `examples/bun-rate-limit/package.json`, `examples/bun-rate-limit/tsconfig.json`, `examples/deno-sensitive-info/README.md`, `examples/deno-sensitive-info/deno.json`, `examples/deno-sensitive-info/server.ts`, `examples/deno-sensitive-info/tsconfig.json`

Host AI hard rules:
- Without repo_clone_verified=true, do not claim that the source code has been read.
- Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts.
- Without quick_start_verified=true, do not claim that the Quick Start path has run successfully.

## Doramagic Pitfall Constraints

These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes.

### Constraint 1: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: Dependency Dashboard
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: Dependency Dashboard. Context: Observed when using node, docker
- Why it matters: Developers may fail before the first successful local run: Dependency Dashboard
- Evidence: failure_mode_cluster:github_issue | https://github.com/arcjet/arcjet-js/issues/5907
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 2: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: arcjet 1.8.0 wont resolve on windows, dist/_virtual/_. folder has a trailing dot
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: arcjet 1.8.0 wont resolve on windows, dist/_virtual/_. folder has a trailing dot. Context: Observed when using node, windows, linux
- Why it matters: Developers may fail before the first successful local run: arcjet 1.8.0 wont resolve on windows, dist/_virtual/_. folder has a trailing dot
- Evidence: failure_mode_cluster:github_issue | https://github.com/arcjet/arcjet-js/issues/6136
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 3: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: v1.3.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.3.0. Context: Source discussion did not expose a precise runtime context.
- Why it matters: Upgrade or migration may change expected behavior: v1.3.0
- Evidence: failure_mode_cluster:github_release | https://github.com/arcjet/arcjet-js/releases/tag/v1.3.0
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 4: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: v1.3.1
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.3.1. Context: Observed during installation or first-run setup.
- Why it matters: Upgrade or migration may change expected behavior: v1.3.1
- Evidence: failure_mode_cluster:github_release | https://github.com/arcjet/arcjet-js/releases/tag/v1.3.1
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 5: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: v1.6.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.6.0. Context: Observed when using node, docker
- Why it matters: Upgrade or migration may change expected behavior: v1.6.0
- Evidence: failure_mode_cluster:github_release | https://github.com/arcjet/arcjet-js/releases/tag/v1.6.0
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 6: Installation risk requires verification

- Trigger: Developers should check this installation risk before relying on the project: v1.7.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.7.0. Context: Observed when using node
- Why it matters: Upgrade or migration may change expected behavior: v1.7.0
- Evidence: failure_mode_cluster:github_release | https://github.com/arcjet/arcjet-js/releases/tag/v1.7.0
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 7: Configuration risk requires verification

- Trigger: Developers should check this configuration risk before relying on the project: v1.5.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v1.5.0. Context: Observed when using node
- Why it matters: Upgrade or migration may change expected behavior: v1.5.0
- Evidence: failure_mode_cluster:github_release | https://github.com/arcjet/arcjet-js/releases/tag/v1.5.0
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.