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/kalinbogatzevski/captain-memo/agents-mdgit clone --depth 1 https://github.com/kalinbogatzevski/captain-memoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/kalinbogatzevski/captain-memo/agents-md)<a href="https://agentmods.dev/instructions/kalinbogatzevski/captain-memo/agents-md"><img src="https://agentmods.dev/badge/instructions/kalinbogatzevski/captain-memo/agents-md.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00809 | $0.00809 |
| Opus 5 | $0.00404 | $0.00404 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
captain-memo 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 6d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Orientation for AI coding agents working on this repository. Humans want CONTRIBUTING.md.
What this project is
Captain Memo is a local-first memory layer for AI coding agents. It keeps one searchable
corpus on your machine — SQLite + sqlite-vec + FTS5 — and every MCP-speaking coding tool on
that machine shares it. What one tool learns, the others recall.
Two moving parts: a background worker (indexes, embeds, summarizes) and an MCP server plus hooks that the AI tool loads. Nothing calls a cloud database; retrieval is local.
Runtime
Bun ≥ 1.1.14, TypeScript. Not Node — bun runs the TypeScript source directly, so there is
no build step for the worker, CLI, or hooks. The only bundling target is the distributable
plugin (bun run build:plugin).
Commands
bun install
bun test # full suite
bun test tests/unit/ # or: bun run test:unit
bun test tests/integration/ # or: bun run test:integration
bun test tests/hooks/ # or: bun run test:hooks
bun run typecheck # tsc --noEmit
bun src/cli/index.ts doctor # health-check a local install
Run bun run typecheck and bun test before proposing a change. Both must be clean.
Handy during development:
bun run worker:dev # worker with --watch, against ./.captain-memo.dev
bun run mcp:start # the MCP server on stdio
bun bin/captain-memo <cmd> # the CLI
Layout
| Path | What lives there |
|---|---|
src/worker/ |
Background worker: indexing, embedding, summarizing, the tick loop |
src/mcp-server.ts |
MCP server the AI tools connect to |
src/hooks/ |
UserPromptSubmit / PreToolUse / Stop hook handlers |
src/cli/ |
captain-memo CLI, including install and connect |
src/services/ |
Embedders, summarizer providers, search, storage |
src/shared/ |
Types and helpers used across the above |
src/migration/ |
Data-format upgrades between versions |
src/dreaming/, src/eval/ |
Consolidation and retrieval evaluation |
tests/ |
unit/, integration/, hooks/ |
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.
- 6d ago First seen · 73 lines · 809 tokens per session scan A 8c798cf3eb86
captain-memo AGENTS.md is an instructions file published in the GitHub repository kalinbogatzevski/captain-memo (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 809 tokens to every session, about $0.0040 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
memem CLAUDE.md
Claude Code instructions for TT-Wang/memem, covering memem — persistent memory & context assembly, auto-recall, context model (v2.8+), tier 1 — profiles (always-injected) and tier 2 — working rules (procedural, citation-ranked).
neurostack CLAUDE.md
Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.
wenlan AGENTS.md
AGENTS.md instructions for 7xuanlu/wenlan, covering agents.md, start here, build and verification, repository invariants and git and release.
rag-rat AGENTS.md
Instructions for cq27-dev/rag-rat, covering agents.md, prefer the rag-rat mcp for code browsing, record durable learnings as rag-rat memories, repo orientation and worktree correctness.
mcp-recall CLAUDE.md
Claude Code instructions for sakebomb/mcp-recall, covering claude.md – mcp-recall, project overview, tech stack, commands and architecture.
kb AGENTS.md
AGENTS.md instructions for hraness/kb, a project described as: A knowledge base for coding agents, built from Markdown, backlinks, semantic search, and Git context.