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/tools-for-agents/recall/agents-mdgit clone --depth 1 https://github.com/tools-for-agents/recallWhat 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 | $0.00911 | $0.00911 |
| Opus 5 | $0.00456 | $0.00456 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
recall 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — recall
🎯 Federated recall across an agent's knowledge. One query across cortex, agent-hq, scout and lens, returning a single token-budgeted briefing. Read-only. Use it first, at the start of a task. Part of tools-for-agents.
Setup
node --version # 22+ required. Nothing to install.
npm test # = node --test
node src/cli.js "some question" # the query IS the verb — there is no `search`
node src/cli.js status # which knowledge stores are reachable
node src/cli.js serve --port 7980 # the console (real, but absent from --help)
npm run mcp # the MCP server, stdio
Zero runtime dependencies, and that is a hard rule. No dependencies in package.json, ever. Node 22+
gives you what you need.
| Env | For |
|---|---|
RECALL_PORT |
serve port (default 7980) |
RECALL_CORTEX_DB / CORTEX_VAULT |
🧠 brain — cortex notes |
RECALL_HQ_URL / HQ_URL |
🛰️ team — agent-hq memory (default http://localhost:7700) |
RECALL_SCOUT_DB / SCOUT_DB |
🧭 reading — scout pages |
RECALL_LENS_DB / LENS_DB |
🔎 code — lens chunks |
Every store is auto-discovered and optional — recall status tells you which ones answered.
recall talks to its siblings over HTTP; it owns no store of its own. It is read-only by design — if you find yourself adding a write path, that belongs in the tool that owns the data.
The rules this repo is built on
1. Only the picture is evidence. Run iris against any UI
change and look at the shot. Audit phone,tablet,desktop, both themes, with --hover.
2. Answer prefers-reduced-motion. The briefing cards enter with animation: rise .28s both. A gate that
waited only for .hit to exist photographed them at ~40% opacity and reported 2.92:1 — a high, on text
that is 16:1 once it lands. That finding was the camera's shutter speed, not a defect. The
@media (prefers-reduced-motion: reduce) { .hit { animation: none } } rule is what makes the render
deterministic — keep it, and keep it below the rules it must beat.
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 · 68 lines · 911 tokens per session scan A 262ac985f35c
recall AGENTS.md is an instructions file published in the GitHub repository tools-for-agents/recall (0 stars, last pushed 28d ago), licensed MIT. It adds 911 tokens to every session, about $0.0046 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
cortex AGENTS.md
AGENTS.md instructions for tools-for-agents/cortex, covering agents.md — cortex, setup, the rules this repo is built on, tests and ci.
scout AGENTS.md
AGENTS.md instructions for tools-for-agents/scout, covering agents.md — scout, setup, the rules this repo is built on, tests and ci.
vetix AGENTS.md
Instructions for HuTa0kj/vetix, covering vetix — project map, repository layout, workflow, extension points and configuration.
tauri-agent-tools CLAUDE.md
Instructions for cesarandreslopez/tauri-agent-tools, covering claude.md, project, commands, key source locations and architecture.
trustabl CLAUDE.md
Instructions for trustabl/trustabl, covering instructions for claude — trustabl, project naming, detection model: five scopes, scanning pipeline and step 1 — recon (cheap, no ast).
trustabl GEMINI.md
Instructions for trustabl/trustabl, a project described as: Fix agent reliability issues across Claude, OpenAI, Google ADK, MCP, LangChain, CrewAI, AutoGen, Pydantic AI, and Vercel AI.