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/pcopu/coco/agents-mdgit clone --depth 1 https://github.com/pcopu/cocoWhat 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 | $0.00351 | $0.00351 |
| Opus 5 | $0.00176 | $0.00176 |
| Sonnet 5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
coco 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.
What it actually says
Repository Memory Notes
Auto Memory Log
- Memory log path:
TELEGRAM_CHAT_MEMORY.jsonl(repo root). - Purpose: store only Telegram-visible chat text (incoming message text/captions, outgoing sends, outgoing edits).
- This is intentionally not a full internal execution transcript.
Session Start Prompt
Use this at the start of a new agent session in this repo:
Load rolling Telegram memory from TELEGRAM_CHAT_MEMORY.jsonl.
Read the latest 200 lines and build a concise working-memory summary:
- active goals
- recent decisions/constraints
- unresolved tasks
- latest verified environment facts
Treat this log as source-of-truth for what was actually shown in Telegram chat.
Runtime Notes
- Auto-writer is implemented in
src/coco/telegram_memory.py. - To override log location, set
COCO_TELEGRAM_MEMORY_LOG_PATH.
Self-Update Safety
- CoCo self-update must treat only tracked or staged changes as a dirty worktree.
Use
git status --porcelain --untracked-files=nofor this check. - Untracked research, temporary files, and backups are user-owned artifacts. They
must not block
/update, and update code must never delete, stash, or clean them. - Keep the local updater in
src/coco/bot.pyand the remote-node updater insrc/coco/agent_rpc.pyaligned when changing update safety behavior. - Preserve regression coverage proving that untracked-only worktrees can update
while modified tracked files still block.
git pull --ff-onlymust remain the final guard against an incoming tracked path overwriting an untracked file.
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 · 35 lines · 351 tokens per session scan A 64980f009588
coco AGENTS.md is an instructions file published in the GitHub repository pcopu/coco (4 stars, last pushed 8d ago), licensed MIT. It adds 351 tokens to every session, about $0.0018 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
sessions-chronicle AGENTS.md
Instructions for supermaciz/sessions-chronicle, covering repository guidelines, where to look first, terminology, project structure & module organization and fast dev loop.
vibe-state-cli AGENTS.md
Instructions for liyoncso-Theone/vibe-state-cli, covering agents.md — vibe-state-cli, project, last session, session start — read these files and persistent knowledge — query before recall.
claude-code CLAUDE.md
Claude Code instructions for nette/claude-code, covering claude.md, project overview, plugin structure, testing plugins locally and hook scripts.
NoLidSleep CLAUDE.md
Instructions for jark006/NoLidSleep, covering claude.md, 项目简介, 构建, release x64 构建 and 架构.
interactive-mcp copilot-instructions.md
Instructions for ttommyth/interactive-mcp, covering interaction with user and ai notes - cursor documentation system.
vibe-state-cli CLAUDE.md
Instructions for liyoncso-Theone/vibe-state-cli, covering claude.md — vibe-state-cli and claude-specific.