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/danielwpz/pokoclaw/agents-mdgit clone --depth 1 https://github.com/danielwpz/pokoclawWrote 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/danielwpz/pokoclaw/agents-md)<a href="https://agentmods.dev/instructions/danielwpz/pokoclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/danielwpz/pokoclaw/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 | $0.02502 | $0.02502 |
| Opus 5 | $0.01251 | $0.01251 |
| Sonnet 5 | $0.00500 | $0.00500 |
| Haiku 4.5 | $0.00250 | $0.00250 |
Grade A, and why
pokoclaw 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 4d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Guidance for coding agents working in this repository.
Project Shape
- TypeScript / Node.js / pnpm project
- Personal AI assistant focused on long-running, observable task execution
- Feishu/Lark is currently the only supported channel
- The codebase is early-stage and should be changed incrementally
Core Rules
- Make the best change that solves the task.
- Preserve existing user work.
- Prioritize code quality, maintainability, extensibility, and product quality above short-term shortcuts.
- Do not reject a refactor just because it is speculative; use judgment and make the change when it improves the result materially.
- If behavior changes, add or update tests.
- If user-facing setup or usage changes, update the relevant repository docs in the same change when practical.
- Keep explanations concrete and tied to actual code paths.
File And Git Safety
- Never use destructive git commands such as
git reset --hardorgit checkout --unless explicitly requested and approved. - Do not amend commits unless the user explicitly asks.
- Never revert changes you did not make.
- If you notice unrelated unexpected modifications, stop and ask how to proceed if they conflict with the task.
- Prefer
apply_patchfor manual file edits. - Do not use Python for file editing when a shell command or
apply_patchis sufficient. - Prefer ASCII when editing files unless the file already uses non-ASCII and there is a clear reason to match it.
Dependency Commands
- When running
pnpm add,pnpm install, or similar dependency-changing commands:- if the command hits a permissions or sandbox problem, request escalated permissions directly
- do not first try to work around it with
--store-diror other local store rewrites - reason: this repository has repeatedly hit false-detour issues from trying to patch pnpm store behavior instead of just requesting the needed permission
Commands
pnpm install- install dependenciespnpm build- TypeScript check (tsc --noEmit)pnpm typecheck- same aspnpm buildpnpm lint- Biome checkspnpm format- Biome write/fixpnpm test- Vitest suitepnpm test:integration- integration testspnpm preflight- build + format + lint + testpnpm start- run the app oncepnpm dev- run the app with watch modepnpm meditation:backtest -- --tick-at <iso> [--lookback-days N | --start-at <iso> --end-at <iso>] [--label name]- run the normal meditation pipeline against a sandbox copy of the live DB/workspace for replay/backtest without mutating live meditation statepnpm meditation:episode-study -- --tick-at <iso> [--lookback-days N | --start-at <iso> --end-at <iso>] [--session-id <id>]... [--top-sessions N] [--label name]- compare multiple candidate friction-episode extraction strategies against real historical session data and write reports under.tmp/meditation-episode-study/
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.
- 4d ago First seen · 198 lines · 2,502 tokens per session scan A 189ae2f9619e
pokoclaw AGENTS.md is an instructions file published in the GitHub repository danielwpz/pokoclaw (141 stars, last pushed 15d ago), licensed Apache-2.0. It adds 2,502 tokens to every session, about $0.0125 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 2026-08-30.
Other instructions, from other repositories
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).
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.
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.