Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/danielguru/repomemory/agents-mdgit clone --depth 1 https://github.com/DanielGuru/repomemoryWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02058 | $0.02058 |
| Opus 5 | $0.01029 | $0.01029 |
| Sonnet 5 | $0.00412 | $0.00412 |
| Haiku 4.5 | $0.00206 | $0.00206 |
Grade A, and why
repomemory AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repomemory — Instructions for AI Coding Agents
This file is for Codex, Copilot Workspace, Devin, and any other AI agent working on this codebase.
Project Overview
repomemory is a CLI tool + MCP server that gives AI coding agents persistent memory for repositories. It creates a .context/ directory with structured knowledge (facts, decisions, regressions, preferences, session logs) that agents can search, write to, and delete from. Features hybrid keyword + semantic search, auto-session capture, intelligent category routing, auto-purge detection, and global developer context (~/.repomemory/global/) that follows you across all repos.
Language: TypeScript (ESM, strict mode)
Runtime: Node.js 20+
Package manager: npm
Build: npm run build (runs tsc + shebang injection via scripts/build.js)
Test: npm test (vitest, 163 tests)
Repository Structure
src/index.ts -> CLI entry point (Commander.js, 11 commands)
src/commands/init.ts -> Scaffolds .context/ directory, exports CLAUDE_MD_BLOCK
src/commands/analyze.ts -> AI-powered repo analysis (core feature)
src/commands/sync.ts -> Git history -> changelog sync with deduplication
src/commands/serve.ts -> Starts MCP server
src/commands/setup.ts -> Configures 7 AI tools (Claude/Cursor/Copilot/Windsurf/Cline/Aider/Continue)
src/commands/status.ts -> Coverage bars, freshness indicators, suggestions
src/commands/wizard.ts -> Interactive guided setup (@clack/prompts)
src/commands/dashboard.ts -> Localhost web dashboard (port 3333) with edit, search, export
src/commands/hook.ts -> Git post-commit hook install/uninstall
src/commands/go.ts -> One-command setup: global profile + init + analyze + setup claude
src/commands/global.ts -> Manage global developer context (list/read/write/delete/export/import)
src/mcp/server.ts -> MCP server with 6 tools + 2 prompts + dual store (repo + global) + session tracking
src/lib/ai-provider.ts -> Multi-provider AI abstraction (Anthropic/OpenAI/Gemini/Grok)
src/lib/embeddings.ts -> Embedding provider abstraction (OpenAI/Gemini) + cosine similarity
src/lib/config.ts -> Configuration loading with Zod validation, global context config, resolveGlobalDir()
src/lib/context-store.ts -> CRUD + delete for .context/ files (6 categories), forAbsolutePath() for global store
src/lib/search.ts -> sql.js (Wasm) FTS5 + optional vector search, hybrid scoring, DB persistence
src/lib/json-repair.ts -> JSON extraction/repair from AI output
src/lib/git.ts -> Git info extraction (execFileSync, no shell injection)
src/lib/repo-scanner.ts -> Repository scanning with .gitignore support
scripts/build.js -> Build script (tsc + shebang injection)
tests/ -> vitest test suite (163 tests)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 152 lines · 2,058 tokens per session scan A f5aada394c24
repomemory AGENTS.md is an instructions file published in the GitHub repository DanielGuru/repomemory (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,058 tokens to every session, about $0.0103 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
memorix GEMINI.md
Instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.
golembot CLAUDE.md
Instructions for 0xranx/golembot, covering golembot — project conventions for claude code, architecture hard constraints, things you must never do, interface change rules and file responsibility boundaries.
packmind packmind-cli-command-structure.instructions.md
Instructions for PackmindHub/packmind: Enforce clear separation of concerns between command definition (parameters and metadata) and handler logic (validation, execution, and output) in apps/cli commands to improve testability, maintainabi... .
packmind packmind-frontend-error-management.instructions.md
Instructions for PackmindHub/packmind: A global error boundary is already configured at the root level (in root.tsx) that automatically catches all page crashes, 404s, and loader failures. This standard defines when and how to use explicit... .
packmind packmind-frontend-navigation-with-react-router.instructions.md
Instructions for PackmindHub/packmind: This codebase uses React Router v7 with organization and space scoping in URLs (e.g., /org/{orgSlug}/space/{spaceSlug}/recipes). To maintain consistency, improve maintainability, and simplify navigati... .
packmind packmind-rest-api-endpoint-design.instructions.md
Instructions for PackmindHub/packmind: Conventions for designing REST API endpoints that are predictable, self-documenting, and aligned with distinct business actions. Favors dedicated action endpoints over generic status updates, and rout... .