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/jommar/memory-mcp/agents-mdgit clone --depth 1 https://github.com/jommar/memory-mcpWhat 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 | $0.00625 | $0.00625 |
| Opus 5 | $0.00313 | $0.00313 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
memory-mcp 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 yesterday.
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents. This file only points at the real docs and lists rules not stated elsewhere — read the linked files before working here.
Read first
| Doc | Covers |
|---|---|
| DESIGN.md | Authoritative design: architecture, data model, reliability engine, tool surface, stack pins (§3), repo layout (§7), session learnings (§11) |
| README.md | Install/run, MEMORY_* env config, maintenance CLI, explorer UI |
| docs/tools.md | Reference for all 10 MCP tools |
| docs/reliability.md | Reliability formula, decay λ/tiers, lifecycle rules behind consolidate |
Rules
- Keep DESIGN.md current. Update it in the same change set when you ship or change a feature — new behavior, replaced decisions, corrected stack/version facts. Stale design = bug.
- Keep this file current too. If your change invalidates any command, path, or claim here, update or delete that line in the same change set — a stale instruction is worse than none.
- Verify like CI does (
.github/workflows/ci.yml, Node 22 + 24):npm run lint && npm run typecheck && npm test; whenui/is touched alsonpm run ui:typecheck && npm run ui:build && npm run ui:test. - Orchestrator sessions live under
.orchestrator/<NN-slug>/(gitignored). Never edit or reuse a past session's directory; number new ones (01-,02-, …) solsorders them. - Node ≥22, TypeScript ESM (
nodenext: relative imports end in.js;verbatimModuleSyntaxrequiresimport type). Stack pins live inpackage.json; decisions in DESIGN.md §2–3.
Tooling gotchas
- There is no eslint/prettier/biome by design —
npm run lintis tsc-based dead-code checking (--noUnusedLocals --noUnusedParameters --noUncheckedSideEffectImports). Don't add a linter or reformat the tree unasked. npm testis not purely unit tests:test/packaging.test.tsrunsnpm run build, packs the tarball, installs it into a temp dir, and drives the compiled bins (dist/cli.js,dist/src/index.js) over stdio. While iterating, run one file:npx vitest run test/core/recall.test.ts(same pattern underui/).- The suite is offline-safe: tests inject fake embedding providers; the only real-model
test (
test/embeddings/local.test.ts) skips itself unless.cache/models/exists.
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.
- yesterday First seen · 41 lines · 625 tokens per session scan A b6b951a19ab4
memory-mcp AGENTS.md is an instructions file published in the GitHub repository jommar/memory-mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 625 tokens to every session, about $0.0031 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.