# mnemonic - 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 mnemonic. 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_0003` supported 0.86
- **Users who want to bring professional workflows into a host AI**: The repo contains Skill documents. Evidence: `.agents/skills/typescript-code-review/SKILL.md`, `skills/mnemonic-rpi-workflow/SKILL.md` Claim: `clm_0004` supported 0.86

## What It Can Do

- **AI Skill / Agent Instruction Asset Library** (Previewable before install): The project contains Skill or Agent instruction files that a host AI can read, useful for bringing professional workflows into hosts like Claude, Codex, or Cursor. Evidence: `.agents/skills/typescript-code-review/SKILL.md`, `skills/mnemonic-rpi-workflow/SKILL.md` Claim: `clm_0001` supported 0.86
- **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_0002` supported 0.86

## How to Start

- `npm install @danielmarbach/mnemonic-mcp` Evidence: `README.md` Claim: `clm_0005` supported 0.86, `clm_0006` supported 0.86
- `npm install @danielmarbach/mnemonic-mcp@0.2.0` Evidence: `README.md` Claim: `clm_0006` supported 0.86
- `npx mnemonic-install-skills --target all --mode copy` Evidence: `README.md` Claim: `clm_0007` supported 0.86, `clm_0009` supported 0.86
- `npx -y -p @danielmarbach/mnemonic-mcp mnemonic-install-skills --target all --mode copy` Evidence: `README.md` Claim: `clm_0008` supported 0.86
- `npx mnemonic-install-skills --target all --mode copy --update` Evidence: `README.md` Claim: `clm_0009` supported 0.86
- `npx mnemonic-install-skills --target all --mode symlink --update` Evidence: `README.md` Claim: `clm_0010` supported 0.86
- `git clone git@github.com:you/mnemonic-vault.git ~/mnemonic-vault` Evidence: `README.md` Claim: `clm_0011` supported 0.86

## Continue-or-Stop Decision Card

- **Current recommendation**: Needs admin / security approval
- **Why**: Continuing may involve secrets, accounts, external services, or sensitive context; get admin or security approval first.

### 30-Second Read

- **What to do now**: Needs admin / security approval
- **Minimum safe next step**: Run Prompt Preview first; if credentials or an enterprise environment are involved, get approval before trialing
- **Do not trust yet**: Research conclusions, citations, and experiment results cannot be trusted before install.
- **Continuing will touch**: Research judgment, Command execution, Host AI configuration

### 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_0003` supported 0.86
- **Target-audience signal: Users who want to bring professional workflows into a host AI** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `.agents/skills/typescript-code-review/SKILL.md`, `skills/mnemonic-rpi-workflow/SKILL.md` Claim: `clm_0004` supported 0.86
- **Capability exists: AI Skill / Agent Instruction Asset Library** (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: `.agents/skills/typescript-code-review/SKILL.md`, `skills/mnemonic-rpi-workflow/SKILL.md` Claim: `clm_0001` 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_0002` 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_0005` supported 0.86, `clm_0006` supported 0.86

### What You Cannot Trust Yet

- **Research conclusions, citations, and experiment results cannot be trusted before install.** (unverified): A research Skill can organize questions and paths, but it cannot replace real literature search, paper verification, and experiment reproduction.
- **Whether it fits your specific research field cannot be trusted directly.** (unverified): The Skill covering many research topics does not mean it is sufficient for your field, source requirements, and credibility standards.
- **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. Evidence: `.agents/skills/typescript-code-review/SKILL.md`, `CLAUDE.md`, `skills/mnemonic-rpi-workflow/SKILL.md`
- **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

- **Research judgment**: Problem decomposition, source paths, experiment paths, conclusion structure, and credibility judgment. Why: A research Skill can make output look more professional but cannot replace real evidence verification.
- **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`
- **Host AI configuration**: The plugin, Skill, or rule-loading config of hosts like Claude/Codex/Cursor/Gemini/OpenCode. Why: Host configuration changes how the AI works afterward and may conflict with the user's existing rules. Evidence: `.agents/skills/typescript-code-review/SKILL.md`, `CLAUDE.md`, `skills/mnemonic-rpi-workflow/SKILL.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`
- **Environment variables / API keys**: Project entry docs explicitly showing API key, token, secret, or account credential configuration. Why: If a real install needs credentials, use test credentials first and go through a permission/compliance review. Evidence: `.mnemonic/notes/multi-provider-embedding-support-plan-and-research-consolida-c1687672.md`, `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**: Verify whether it can correctly frame the research question and evidence boundaries first; do not trust the research output 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.)
- **Back up your host AI configuration first**: Skill, plugin, and rule files may change the default behavior of Claude/Cursor/Codex. (applies when: When there is a plugin manifest, a Skill, or a host rule entrypoint.)
- **Do not use real production credentials**: Once an environment variable / API key enters the host or toolchain, it can create account and compliance risk. (applies when: When environment signals like API, TOKEN, KEY, or SECRET appear.)
- **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.
- **Be ready to remove the host plugin / Skill / rule entrypoint**: If behavior is off after the trial install, you can restore the host AI to its pre-trial state.
- **Keep a source and conclusion verification checklist**: If citations or experiment paths later prove unreliable, you can return to the evidence-boundary stage and re-check.
- **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.
- **Be ready to revoke test API keys or tokens**: If test credentials leak or are misused, you can cut losses quickly.
- **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_0012` 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_0013` 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

- **AI Skill / Agent Instruction Asset Library**: Use role_skill_index / evidence_index to help the user pick a usable role, Skill, or workflow first. Boundary: Can be experienced via a pre-install Prompt. Evidence: `.agents/skills/typescript-code-review/SKILL.md`, `skills/mnemonic-rpi-workflow/SKILL.md` Claim: `clm_0001` supported 0.86
- **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_0002` supported 0.86

### Context Scale

- Total files: 230
- Important-file coverage: 40/230
- Evidence index entries: 80
- Role / Skill entries: 2

### 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 mnemonic, 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 mnemonic 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 mnemonic, 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 2 role / Skill / project-doc entries.

- **typescript-code-review** (skill): Review TypeScript for type safety, security, performance, maintainability. Makes invalid states unrepresentable via branded types, discriminated unions, template literals, satisfies, infer. Use for TypeScript review, type audits, antipatterns, type-level correctness. Activation hint: When the user's task is highly relevant to the workflow described by “typescript-code-review”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/typescript-code-review/SKILL.md`
- **mnemonic-rpi-workflow** (skill): mnemonic RPIR research-plan-implement-review workflow. Use for multi-step feature/bugfix work, subagent handoffs, plan-heavy tasks, RPIR artifacts. Review phase: fresh-context subagent with adversarial posture for constraint violation hunting. Activation hint: When the user's task is highly relevant to the workflow described by “mnemonic-rpi-workflow”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/mnemonic-rpi-workflow/SKILL.md`

## Evidence Index

- Indexed 80 evidence entries.

- **mnemonic** (documentation): A local MCP memory server backed by plain markdown files, synced via git. No database. Project-scoped memory with hybrid semantic, exact-match, and relationship-aware recall. Evidence: `README.md`
- **Package** (package_manifest): { "name": "@danielmarbach/mnemonic-mcp", "version": "0.36.0", "description": "A local MCP memory server backed by markdown + JSON files, synced via git", "type": "module", "repository": { "type": "git", "url": "git+https://github.com/danielmarbach/mnemonic.git" }, "publishConfig": { "registry": "https://registry.npmjs.org", "access": "public" }, "files": "build", "skills", "scripts/install-skills.mjs", "CHANGELOG.md", "README.md", "LICENSE" , "bin": { "mnemonic": "build/index.js", "mnemonic-install-skills": "scripts/install-skills.mjs" }, "scripts": { "build": "npm run typecheck && tsc && chmod 755 build/index.js", "build:clean": "tsc --build --clean && npm run build", "build:fast": "tsc &&… Evidence: `package.json`
- **TypeScript Code Review** (skill_instruction): Review TypeScript code with a focus on making invalid states unrepresentable . The type system is the most powerful correctness tool available — when types prevent invalid states at compile time, LLMs and humans alike produce fewer bugs because mistakes don't compile. Evidence: `.agents/skills/typescript-code-review/SKILL.md`
- **RPIR Workflow: Research → Plan → Implement → Review** (skill_instruction): RPIR Workflow: Research → Plan → Implement → Review Evidence: `skills/mnemonic-rpi-workflow/SKILL.md`
- **RTK Rust Token Killer - Token-Optimized Commands** (documentation): RTK Rust Token Killer - Token-Optimized Commands Evidence: `CLAUDE.md`
- **Contributing to mnemonic** (documentation): Thank you for contributing to mnemonic. This guide covers the conventions, workflows, and expectations for working on the project. Evidence: `CONTRIBUTING.md`
- **License** (source_file): Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ Evidence: `LICENSE`
- **Architecture** (documentation): mnemonic is a file-first MCP memory server. It stores notes as markdown, keeps embeddings as local JSON, routes reads and writes across a main vault and optional project vaults, and uses git as the synchronization and audit layer instead of a database. Evidence: `ARCHITECTURE.md`
- **Mnemonic Mcp** (source_file): class MnemonicMcp < Formula desc "Local MCP memory server backed by markdown + JSON files, synced via git" homepage "https://github.com/danielmarbach/mnemonic" url "https://registry.npmjs.org/@danielmarbach/mnemonic-mcp/-/mnemonic-mcp-0.36.0.tgz" sha256 "fee8e517aee82f17aeb1186a2b929932084c576209c1713f8f634bd1a37715c4" license "Apache-2.0" ⋮---- depends on "node" ⋮---- def install system " {Formula "node" .opt bin}/npm", "install", "--omit=dev", "--ignore-scripts" libexec.install Dir " " bin/"mnemonic" .write <<~EOS ⋮---- exec " {Formula "node" .opt bin}/node" " {libexec}/build/index.js" "$@" ⋮---- chmod 0755, bin/"mnemonic" ⋮---- test do assert match "Mnemonic Migration Tool", shell output… Evidence: `Formula/mnemonic-mcp.rb`
- **Compose** (source_file): services: ollama: image: ollama/ollama restart: unless-stopped ports: - "11434:11434" volumes: - ollama-data:/root/.ollama ollama-init: image: curlimages/curl:latest entrypoint: "/bin/sh", "-c" depends on: - ollama command: " echo 'Waiting for Ollama to start...' && sleep 10 && for i in 1 2 3 4 5; do echo \"Pulling nomic-embed-text-v2-moe attempt $i/5 ...\" && if curl -sf -X POST http://ollama:11434/api/pull -d '{\"name\": \"nomic-embed-text-v2-moe\"}'; then echo 'Model pulled successfully' && exit 0 fi && echo 'Not ready yet, retrying...' && sleep 10 done && echo 'Failed to pull model after 5 attempts' && exit 1 " mnemonic: build: . stdin open: true tty: false depends on: ollama-init: cond… Evidence: `compose.yaml`
- **Install Skills** (source_file): function printUsage ⋮---- function normalizePath inputPath ⋮---- function parseArgs argv ⋮---- async function pathExists targetPath ⋮---- async function discoverSkills ⋮---- function resolveTargetDirs target, customTargetDirs ⋮---- async function installSkill ⋮---- async function main Evidence: `scripts/install-skills.mjs`
- **Attached Storage** (source_file): import path from "path"; import { simpleGit } from "simple-git"; import { memoryId, type MemoryId } from "./brands.js"; import { Storage, type Note, type NoteStorage, type EmbeddingRecord } from "./storage.js"; import type { NoteProjection } from "./structured-content.js"; import { attempt, debugLog, getErrorMessage } from "./error-utils.js"; import { InvalidBranchNameError, AttachedVaultReadOnlyError } from "./domain-errors.js"; ⋮---- export function validateBranch branch: string : void ⋮---- export class AttachedStorage implements NoteStorage ⋮---- constructor baseStorage: Storage, repoStorage: Storage, repoPath: string, branch: string, notesRelDir: string, writable: boolean = false, ⋮---… Evidence: `src/attached-storage.ts`
- **Config** (source_file): import fs from "fs/promises"; import path from "path"; import { z } from "zod"; ⋮---- import { attempt, attemptSync, debugLog, getErrorMessage } from "./error-utils.js"; import { CONSOLIDATION MODES, PROJECT POLICY SCOPES, PROTECTED BRANCH BEHAVIORS, type ProjectMemoryPolicy, } from "./project-memory-policy.js"; import type { ProjectIdentityOverride } from "./project.js"; import type { ProjectAttachmentConfig } from "./vault.js"; import { attachmentSlug } from "./brands.js"; ⋮---- export type MutationPushMode = "all" "main-only" "none"; ⋮---- export interface MnemonicConfig { schemaVersion: string; reindexEmbedConcurrency: number; mutationPushMode: MutationPushMode; projectMemoryPolicies: R… Evidence: `src/config.ts`
- **Consolidate** (source_file): import type { Note, Relationship } from "./storage.js"; import type { ConsolidationMode } from "./project-memory-policy.js"; import type { ConsolidateClassification } from "./structured-content.js"; import { daysSince } from "./date-utils.js"; ⋮---- export type MergeRisk = typeof MERGE RISKS number ; ⋮---- export interface ConsolidateNoteEvidence { id: string; title: string; lifecycle: "temporary" "permanent"; role?: Note "role" ; ageDays: number; superseded: boolean; supersededBy?: string; supersededCount?: number; relatedCount: number; classification?: ConsolidateClassification; warnings?: string ; mergeRisk: MergeRisk; } ⋮---- function noteAgeDays updatedAt: string, now: Date = new Date… Evidence: `src/consolidate.ts`
- **Embeddings** (source_file): import type { EmbeddingCompatibilityKey, EmbeddingDimensions, EmbeddingMetric, EmbeddingModelId, EmbeddingProviderId, } from "./brands.js"; import { embeddingCompatibilityKey, embeddingDimensions, embeddingMetric, embeddingModelId, embeddingProviderId, } from "./brands.js"; import { EmbeddingConfigurationError, EmbeddingDimensionMismatchError, EmbeddingProviderError, OllamaUrlError, } from "./domain-errors.js"; import type { EmbeddingRecord } from "./storage.js"; import { z } from "zod"; ⋮---- export type EmbeddingProviderKind = typeof EMBEDDING PROVIDER IDS number ; ⋮---- export type EmbeddingMetricValue = typeof EMBEDDING METRICS number ; ⋮---- export interface EmbeddingIdentity { readonl… Evidence: `src/embeddings.ts`
- **Index** (source_file): import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; ⋮---- import { registerAllTools } from "./tools/index.js"; import { registerPrompts } from "./prompts.js"; import { createServerContext, readPackageVersion } from "./context.js"; import { startServer } from "./startup.js"; import { isCliCommand, showHelp, rejectUnknownCommand, runCliCommand } from "./cli/dispatch.js"; Evidence: `src/index.ts`
- **Project Introspection** (source_file): import type { Note } from "./storage.js"; import type { EffectiveNoteMetadata } from "./role-suggestions.js"; import { MS PER DAY } from "./date-utils.js"; ⋮---- type ScoringMetadata = Pick ; ⋮---- function explicitAlwaysLoad metadata?: ScoringMetadata ⋮---- function roleBonus role: EffectiveNoteMetadata "role" , source: EffectiveNoteMetadata "roleSource" , explicitBonuses: Partial , number , suggestedBonuses: Partial , number , : number ⋮---- function importanceBonus importance: EffectiveNoteMetadata "importance" , source: EffectiveNoteMetadata "importanceSource" , explicitBonuses: Partial , number , suggestedBonuses: Partial , number , : number ⋮---- export function normalizeKeyword keywo… Evidence: `src/project-introspection.ts`
- **Project** (source_file): import { execFile } from "child process"; import { promisify } from "util"; import path from "path"; import type { ProjectId } from "./brands.js"; import { projectId } from "./brands.js"; import { attempt } from "./error-utils.js"; ⋮---- export type ProjectSource = "git-remote" "git-remote-override" "git-folder" "folder"; ⋮---- export interface ProjectInfo { id: ProjectId; name: string; source: ProjectSource; remoteName?: string; } ⋮---- export interface ProjectIdentityOverride { remoteName: string; updatedAt: string; } ⋮---- export interface ProjectDetectionOptions { getProjectIdentityOverride?: projectId: string = Promise ; } ⋮---- export interface ProjectIdentityResolution { project: Pro… Evidence: `src/project.ts`
- **Projections** (source_file): import type { Note, NoteStorage } from "./storage.js"; import type { NoteProjection } from "./structured-content.js"; import { memoryId } from "./brands.js"; ⋮---- export function extractProjectionSummary note: Note : string ⋮---- // Strip leading heading lines Title, Title, etc. from the body ⋮---- // Step 2: first bullet list block converted to plain text ⋮---- // Step 3: first 200 chars of plain text body ⋮---- // ── Heading extraction ──────────────────────────────────────────────────────── ⋮---- / Extract headings from markdown content. Returns plain text, in order, deduplicated, max 8 headings. / export function extractHeadings markdown: string : string ⋮---- // ── Projection text ───… Evidence: `src/projections.ts`
- **Recall** (source_file): import type { Vault } from "./vault.js"; import type { EffectiveNoteMetadata } from "./role-suggestions.js"; import { computeLexicalScore, tokenize } from "./lexical.js"; import { MS PER DAY } from "./date-utils.js"; import { UnknownRelationshipTypeError } from "./domain-errors.js"; ⋮---- import type { Confidence } from "./structured-content.js"; import type { RelationshipType } from "./storage.js"; ⋮---- export interface TemporalQueryHint { windowDays: number; maxBoost: number; confidence: Confidence; filterWindowDays?: number; } ⋮---- export interface ScoredRecallCandidate { id: string; identityKey?: string; score: number; semanticScoreForPromotion?: number; semanticRank?: number; lexical… Evidence: `src/recall.ts`
- **Storage** (source_file): import fs from "fs/promises"; import path from "path"; import { randomUUID } from "crypto"; import matter from "gray-matter"; import type { NoteProjection } from "./structured-content.js"; import { validateEmbeddingRecord, validateNoteProjection, validateRelatedTo, } from "./validation.js"; import type { EmbeddingCompatibilityKey, EmbeddingDimensions, EmbeddingMetric, EmbeddingModelId, EmbeddingProviderId, ISO8601DateString, MemoryId, } from "./brands.js"; import { memoryId, isoDateString, isValidMemoryId } from "./brands.js"; import { attempt } from "./error-utils.js"; import { AtomicWriteInProgressError, MalformedNoteError, InvalidNoteIdError, } from "./domain-errors.js"; ⋮---- export typ… Evidence: `src/storage.ts`
- **Vault** (source_file): import fs from "fs/promises"; import path from "path"; import { simpleGit } from "simple-git"; ⋮---- import { attempt, debugLog, getErrorMessage } from "./error-utils.js"; import { Storage, type Note, type NoteStorage } from "./storage.js"; import { memoryId, type AttachmentSlug } from "./brands.js"; import { GitOps } from "./git.js"; import { AttachedStorage } from "./attached-storage.js"; import { expandHomePath } from "./paths.js"; ⋮---- export type VaultProvenance = "main" "project-local" "project-attached"; ⋮---- export interface AttachmentRef { projectSlug: AttachmentSlug; projectName: string; localPath: string; branch: string; branchTipHash: string; writable?: boolean; pushBranch?: s… Evidence: `src/vault.ts`
- **Embed** (source_file): import { promises as fs } from "fs"; import { checkEmbeddingCompatibility, currentEmbeddingIdentity, embed, embeddingMetadata, } from "../embeddings.js"; import { memoryId, isoDateString } from "../brands.js"; import { getOrBuildProjection } from "../projections.js"; import { attempt, getErrorMessage } from "../error-utils.js"; import type { NoteStorage, Note } from "../storage.js"; import type { ServerContext } from "../server-context.js"; ⋮---- export interface FailedEmbedding { id: string; error: string; } ⋮---- export async function embedTextForNote storage: NoteStorage, note: Note : Promise ⋮---- export async function embedMissingNotes ctx: ServerContext, storage: NoteStorage, noteIds?… Evidence: `src/helpers/embed.ts`
- **Index** (source_file): import { randomUUID } from "crypto"; import type { Note, NoteLifecycle, NoteRole } from "../storage.js"; import type { MemoryId } from "../brands.js"; import { memoryId } from "../brands.js"; import type { RelationshipPreview, RetrievalEvidence } from "../structured-content.js"; ⋮---- export function slugify text: string : string ⋮---- export function makeId title: string : MemoryId ⋮---- export function describeLifecycle lifecycle: NoteLifecycle : string ⋮---- export function formatNote note: Note, score?: number, showRawRelated = true : string ⋮---- export function formatTemporalHistory history: Array , : string ⋮---- export function formatRelationshipPreview preview: RelationshipPreview… Evidence: `src/helpers/index.ts`
- **Project** (source_file): import { z } from "zod"; import path from "path"; import { simpleGit } from "simple-git"; import { detectProject, resolveProjectIdentity, type ProjectIdentityResolution, } from "../project.js"; import type { ServerContext } from "../server-context.js"; import type { ProjectRef } from "../structured-content.js"; import type { Vault } from "../vault.js"; import type { WriteScope } from "../project-memory-policy.js"; import { invalidateActiveProjectCache } from "../cache.js"; import { checkBranchChange } from "../branch-tracker.js"; import { backfillEmbeddingsAfterSync, removeStaleEmbeddings } from "./embed.js"; import { expandHomePath } from "../paths.js"; import { attempt as attemptFn, getEr… Evidence: `src/helpers/project.ts`
- **Vault** (source_file): import type { Note, NoteLifecycle, NoteRole } from "../storage.js"; import type { ServerContext } from "../server-context.js"; import type { Vault } from "../vault.js"; import type { PersistenceStatus } from "../structured-content.js"; import { getOrBuildVaultNoteList } from "../cache.js"; import { resolveProject } from "./project.js"; import { formatCommitBody, commitVaultWithProtection, checkVaultProtectedBranch, } from "./git-commit.js"; import { pushAfterMutation, buildMutationRetryContract, buildPersistenceStatus, } from "./persistence.js"; import { ProtectedBranchError } from "../domain-errors.js"; import { filterRelationships } from "../consolidate.js"; import { summarizePreview } fr… Evidence: `src/helpers/vault.ts`
- **Consolidate** (source_file): import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { ConsolidateResultSchema } from "../structured-content.js"; import { projectParam, resolveProject, ensureBranchSynced } from "../helpers/project.js"; import { collectVisibleNotes, projectNotFoundResponse } from "../helpers/vault.js"; import { CONSOLIDATION MODES, resolveConsolidationMode } from "../project-memory-policy.js"; import { invalidateActiveProjectCache } from "../cache.js"; import { detectDuplicates, findClusters, suggestMerges, executeMerge, pruneSuperseded, dryRunAll, } from "./consolidate-helpers.js"; export functi… Evidence: `src/tools/consolidate.ts`
- **Detect Project** (source_file): import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { resolveProjectIdentityForCwd as resolveProjectIdentityForCwdFromModule } from "../helpers/project.js"; import { projectNotFoundResponse, formatProjectPolicyLine as formatProjectPolicyLineFromModule, } from "../helpers/vault.js"; import type { ProjectIdentityResolution } from "../project.js"; import { ProjectIdentityResultSchema, type ProjectIdentityResult } from "../structured-content.js"; ⋮---- export function formatProjectIdentityText identity: ProjectIdentityResolution : string ⋮---- export function registerDetectProjectToo… Evidence: `src/tools/detect-project.ts`
- **Forget** (source_file): import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { NoteIdSchema, ForgetResultSchema, type ForgetResult, type MutationRetryContract, } from "../structured-content.js"; import { projectParam, resolveProject, noteProjectRef, ensureBranchSynced, } from "../helpers/project.js"; import { memoryId } from "../brands.js"; import { formatCommitBody, commitVaultWithProtection, checkVaultProtectedBranch, } from "../helpers/git-commit.js"; import { buildMutationRetryContract, formatRetrySummary, pushAfterMutation, } from "../helpers/persistence.js"; import { removeRelationshipsToNoteIds, a… Evidence: `src/tools/forget.ts`
- **Index** (source_file): import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; ⋮---- import { registerDetectProjectTool } from "./detect-project.js"; import { registerGetProjectIdentityTool } from "./get-project-identity.js"; import { registerSetProjectIdentityTool } from "./set-project-identity.js"; import { registerListMigrationsTool, registerExecuteMigrationTool } from "./migration.js"; import { registerSetProjectMemoryPolicyTool, registerGetProjectMemoryPolicyTool, } from "./policy.js"; import { registerRememberTool } from "./remember.js"; import { registerRecallTool } from "./recall.js"; import { registerUpdateTool } from "./update.… Evidence: `src/tools/index.ts`
- **Recall Helpers** (source_file): import type { Note, NoteLifecycle } from "../storage.js"; import type { Vault } from "../vault.js"; import { getEffectiveMetadata } from "../role-suggestions.js"; import { computeRecallMetadataBoost, recallCandidateIdentity, type ScoredRecallCandidate, type TemporalQueryHint, shouldApplyTemporalFiltering, computeTemporalRecencyBoost, isWithinTemporalFilterWindow, } from "../recall.js"; import { getOrBuildProjection } from "../projections.js"; import { attempt } from "../error-utils.js"; import { getSessionCachedProjection, setSessionCachedProjection, getSessionCachedProjectionTokens, setSessionCachedProjectionTokens, getOrBuildVaultNoteList, } from "../cache.js"; import { tokenize, computeL… Evidence: `src/tools/recall-helpers.ts`
- **Recall** (source_file): import { z } from "zod"; import { performance } from "perf hooks"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import type { Vault } from "../vault.js"; import type { Note, NoteLifecycle, RelationshipType } from "../storage.js"; import { memoryId } from "../brands.js"; import { Confidence, RecallResult, RecallResultSchema, RetrievalEvidence, RelationshipPreview, ProjectRef, type RecallRetrievalCoverage, } from "../structured-content.js"; import { checkEmbeddingCompatibility, currentEmbeddingIdentity, embed, safeCosineSimilarity, } from "../embeddings.js"; import { detectTemporalQueryHint, shouldApplyTem… Evidence: `src/tools/recall.ts`
- **Remember** (source_file): import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { NOTE LIFECYCLES, NOTE ROLES, type Note } from "../storage.js"; import { isoDateString } from "../brands.js"; import { getErrorMessage, attempt } from "../error-utils.js"; import { embed, embeddingMetadata } from "../embeddings.js"; import { invalidateActiveProjectCache, getRecentSessionNoteAccesses, getSessionCachedNote, getRecentSessionAccessNote, } from "../cache.js"; import { suggestAutoRelationships } from "../auto-relate.js"; import { MarkdownLintError, cleanMarkdown } from "../markdown.js"; import { resolveWriteScope, WR… Evidence: `src/tools/remember.ts`
- **Update** (source_file): import { z } from "zod"; import type { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; import type { ServerContext } from "../server-context.js"; import { ensureBranchSynced, resolveProject, noteProjectRef, projectParam, } from "../helpers/project.js"; import { formatCommitBody, commitVaultWithProtection, checkVaultProtectedBranch, } from "../helpers/git-commit.js"; import { buildPersistenceStatus, buildMutationRetryContract, formatPersistenceSummary, pushAfterMutation, } from "../helpers/persistence.js"; import { embedTextForNote } from "../helpers/embed.js"; import { memoryId, isoDateString } from "../brands.js"; import { cleanMarkdown, MarkdownLintError } from "../markdown.js… Evidence: `src/tools/update.ts`
- **mnemonic — Agent Context** (documentation): ⚠️ WHEN WORKING ON MNEMONIC: Always test changes with local MCP server first npm run mcp:local or scripts/mcp-local.sh Evidence: `AGENT.md`
- **Changelog** (documentation): All notable changes to mnemonic will be documented in this file. Evidence: `CHANGELOG.md`
- **Contributor Covenant Code of Conduct** (documentation): Contributor Covenant Code of Conduct Evidence: `CODE_OF_CONDUCT.md`
- **Plan** (documentation): ✅ Data format robustness and migration strategy Evidence: `PLAN.md`
- **Mnemonic Memory System** (documentation): No system prompt required. Mnemonic's tools are self-describing — each tool includes "use when" / "do not use when" guidance, behavioral annotations, and typed schemas. Evidence: `SYSTEM_PROMPT.md`
- **TypeScript Common Anti-Patterns** (documentation): Mistakes and anti-patterns to avoid, with better alternatives. Evidence: `.agents/skills/typescript-code-review/references/common-antipatterns.md`
- **Making Invalid States Unrepresentable** (documentation): Making Invalid States Unrepresentable Evidence: `.agents/skills/typescript-code-review/references/impossible-states.md`
- **TypeScript Performance Tips** (documentation): Runtime and compilation performance strategies. Both matter — slow builds hurt developer experience, slow runtime hurts users. Evidence: `.agents/skills/typescript-code-review/references/performance-tips.md`
- **TypeScript Security Checklist** (documentation): Security considerations for TypeScript code reviews. Check these during every review. Evidence: `.agents/skills/typescript-code-review/references/security-checklist.md`
- **Start** (documentation): Orient on the current state of the mnemonic project before doing any work. Evidence: `.claude/commands/start.md`
- **Design** (documentation): Phase 5 adds a lightweight in-memory session cache src/cache.ts that eliminates redundant listNotes + listEmbeddings I/O across tool calls within a single MCP session. Evidence: `.mnemonic/notes/active-session-project-cache-single-in-memory-vault-cache-pe-7463f124.md`
- **Apply Bounded Rrf Hybrid Recall Alignment 0175C033** (documentation): Implements the endorsed one-shot plan plan-one-shot-bounded-rrf-hybrid-recall-alignment-7aa73aaa . Evidence: `.mnemonic/notes/apply-bounded-rrf-hybrid-recall-alignment-0175c033.md`
- **Automatic Branch Change Detection And Sync 89F4Da23** (documentation): Automatic branch change detection and sync now applies to cwd -aware memory operations plus migration execution, not literally every tool. Evidence: `.mnemonic/notes/automatic-branch-change-detection-and-sync-89f4da23.md`
- **Bug fixed: update tool created empty commits and wasted embeddings on no-op changes** (documentation): Bug fixed: update tool created empty commits and wasted embeddings on no-op changes Evidence: `.mnemonic/notes/bug-fix-update-tool-no-op-detection-1031c864.md`
- **Priority P1 - Build and Documentation Enhancements** (documentation): Priority P1 - Build and Documentation Enhancements Evidence: `.mnemonic/notes/build-process-documentation-improvements-7cf12703.md`
- **Retrieval channels** (documentation): Supersede fragmented RRF and hybrid-recall notes with the current implemented design and its product constraints. Evidence: `.mnemonic/notes/canonical-design-bounded-rrf-hybrid-recall-172a96ab.md`
- **Centralized Mutation Guards for Multi-Vault Operations** (documentation): Centralized Mutation Guards for Multi-Vault Operations Evidence: `.mnemonic/notes/centralized-mutation-guards-for-multi-vault-operations-a35f27a2.md`
- **Changelog writing principles** (documentation): Changelog is a curated, user-focused log of notable changes — not a raw commit log. Evidence: `.mnemonic/notes/changelog-writing-principles-87cdbc5b.md`
- **Ci Create Release Checkout Fails Fetching Tag Ref Over Https 64Dbc3B8** (documentation): The create-release job in .github/workflows/publish.yml fails when workflow dispatch is triggered targeting a tag ref e.g. v0.5.0 in the GitHub UI. Evidence: `.mnemonic/notes/ci-create-release-checkout-fails-fetching-tag-ref-over-https-64dbc3b8.md`
- **Consolidated from:** (documentation): Consolidated operational guidance for CI-safe MCP integration tests and artifact-first CI failure learning in mnemonic. Evidence: `.mnemonic/notes/ci-safe-mcp-integration-and-failure-learning-workflow-91431beb.md`
- **Tool design** (documentation): consolidate merges overlapping memories into a canonical note and retires the sources. Evidence: `.mnemonic/notes/consolidate-tool-design-execute-merge-behavior-idempotency-a-0911e2cd.md`
- **Priority P1 - Create Comprehensive Integration Test Suite** (documentation): Priority P1 - Create Comprehensive Integration Test Suite Evidence: `.mnemonic/notes/create-integration-test-suite-b8b73b69.md`
- **Decision: expose trust evidence at decision points via opt-in enrichment** (documentation): Decision: expose trust evidence at decision points via opt-in enrichment Evidence: `.mnemonic/notes/decision-expose-trust-evidence-at-decision-points-via-opt-in-244d8317.md`
- **Decision: Phase 2 recall scoring uses RRF with dense rank tie handling** (documentation): Decision: Phase 2 recall scoring uses RRF with dense rank tie handling Evidence: `.mnemonic/notes/decision-phase-2-recall-scoring-uses-rrf-with-dense-rank-tie-7969c37d.md`
- **The bug fixed 2026-03-12** (documentation): Mnemonic's git operations must never commit files outside the vault's own scope, even if such files happen to be staged in the same repository e.g. source edits made while dogfooding . Evidence: `.mnemonic/notes/design-principle-git-commits-must-only-touch-mnemonic-manage-cecb8d11.md`
- **Devcontainer Uses Node Feature Major 2 And Locked Npm Instal 40Dc0Fe5** (documentation): The repository devcontainer should use ghcr.io/devcontainers/features/node:2 with version: "24" , matching CI's Node 24 runtime while staying on the current major version of the official Node feature. Evidence: `.mnemonic/notes/devcontainer-uses-node-feature-major-2-and-locked-npm-instal-40dc0fe5.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`, `package.json`, `.agents/skills/typescript-code-review/SKILL.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`, `package.json`, `.agents/skills/typescript-code-review/SKILL.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.

- **Overview and Installation**: importance `high`
  - source_paths: README.md, package.json, Dockerfile, compose.yaml, Formula/mnemonic-mcp.rb
- **Vault Architecture and Data Model**: importance `high`
  - source_paths: ARCHITECTURE.md, src/vault.ts, src/storage.ts, src/attached-storage.ts, src/project.ts
- **Recall, Embeddings, and AI Integration**: importance `high`
  - source_paths: src/recall.ts, src/tools/recall.ts, src/tools/recall-helpers.ts, src/embeddings.ts, src/helpers/embed.ts
- **RPIR Workflow, MCP Tools, CLI, and Failure Modes**: importance `high`
  - source_paths: skills/mnemonic-rpi-workflow/SKILL.md, src/tools/index.ts, src/tools/remember.ts, src/tools/update.ts, src/tools/consolidate.ts

## Repo Inspection Evidence

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `ecb00a843ce28cb077157ac66d26b42e38df1c26`
- inspected_files: `Dockerfile`, `README.md`, `package.json`, `src/attached-storage.ts`, `src/auto-relate.ts`, `src/branch-tracker.ts`, `src/brands.ts`, `src/cache.ts`, `src/cli/dispatch.ts`, `src/cli/import-claude-memory.ts`, `src/cli/migrate.ts`, `src/config.ts`, `src/consolidate.ts`, `src/context.ts`, `src/date-utils.ts`, `src/domain-errors.ts`, `src/embeddings.ts`, `src/error-utils.ts`, `src/git-constants.ts`, `src/git.ts`

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/danielmarbach/mnemonic/issues/13
- 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: v0.33.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v0.33.0. Context: Observed when using node, docker
- Why it matters: Upgrade or migration may change expected behavior: v0.33.0
- Evidence: failure_mode_cluster:github_release | https://github.com/danielmarbach/mnemonic/releases/tag/v0.33.0
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 3: Configuration risk requires verification

- Trigger: Developers should check this configuration risk before relying on the project: v0.32.0
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v0.32.0. Context: Source discussion did not expose a precise runtime context.
- Why it matters: Upgrade or migration may change expected behavior: v0.32.0
- Evidence: failure_mode_cluster:github_release | https://github.com/danielmarbach/mnemonic/releases/tag/v0.32.0
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 4: Capability evidence risk requires verification

- Trigger: README/documentation is current enough for a first validation pass.
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: capability.assumptions | https://github.com/danielmarbach/mnemonic
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 5: Security or permission risk requires verification

- Trigger: no_demo
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: downstream_validation.risk_items | https://github.com/danielmarbach/mnemonic
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 6: Security or permission risk requires verification

- Trigger: no_demo
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: risks.scoring_risks | https://github.com/danielmarbach/mnemonic
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 7: Runtime risk requires verification

- Trigger: Developers should check this performance risk before relying on the project: v0.30.1
- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: v0.30.1. Context: Source discussion did not expose a precise runtime context.
- Why it matters: Upgrade or migration may change expected behavior: v0.30.1
- Evidence: failure_mode_cluster:github_release | https://github.com/danielmarbach/mnemonic/releases/tag/v0.30.1
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.