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/fmbenhassine/chessclaw/agents-mdgit clone --depth 1 https://github.com/fmbenhassine/chessclawWrote 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/fmbenhassine/chessclaw/agents-md)<a href="https://agentmods.dev/instructions/fmbenhassine/chessclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/fmbenhassine/chessclaw/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 | $0.00447 | $0.00447 |
| Opus 5 | $0.00224 | $0.00224 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
chessclaw 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 3d 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
ChessClaw
Personal Codex assistant. See README.md for setup and usage. See docs/REQUIREMENTS.md for architecture decisions.
Quick Context
Single Node.js process that connects to Telegram, routes messages to Codex SDK running in Apple Container (Linux VMs). One configured chat talks to one assistant workspace.
Key Files
| File | Purpose |
|---|---|
src/index.ts |
Main app: Telegram connection, single-channel routing, IPC |
src/config.ts |
Trigger pattern, paths, intervals |
src/container-runner.ts |
Spawns agent containers with mounts |
src/task-scheduler.ts |
Runs scheduled tasks |
src/db.ts |
SQLite operations |
src/telegram.ts |
Telegram transport and message delivery |
assistant/AGENTS.md |
Assistant memory and behavior instructions |
Operating Notes
- Prefer
assistant/AGENTS.mdfor runtime instructions and memory. - Run commands directly when asked; do not hand off command execution.
Slash Commands
Treat these commands as aliases:
/setup-> execute.codex/skills/setup/SKILL.md/customize-> execute.codex/skills/customize/SKILL.md/debug-> execute.codex/skills/debug/SKILL.md
Development
npm run dev # Run with hot reload
npm run build # Compile TypeScript
./container/build.sh # Rebuild agent container
Service management:
launchctl load ~/Library/LaunchAgents/dev.chessclaw.plist
launchctl unload ~/Library/LaunchAgents/dev.chessclaw.plist
Container Build Cache
Apple Container's build cache can retain stale COPY layers. For a truly clean rebuild:
container builder stop && container builder rm && container builder start
./container/build.sh
Verify rebuilt source was copied:
container run -i --rm --entrypoint wc chessclaw-agent:latest -l /app/src/index.ts
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.
- 3d ago First seen · 63 lines · 447 tokens per session scan A 40d85f6f43ae
chessclaw AGENTS.md is an instructions file published in the GitHub repository fmbenhassine/chessclaw (5 stars, last pushed 5mo ago), licensed MIT. It adds 447 tokens to every session, about $0.0022 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
dotskills AGENTS.md
AGENTS.md instructions for vincentkoc/dotskills, covering agents.md, repository purpose, mandatory contribution flow, skill standards and openai metadata defaults.
pynchy AGENTS.md
Instructions for crypdick/pynchy, covering pynchy, architectural direction, deployment awareness, quick context and key files.
Cerebro AGENTS.md
Instructions for AgenticFirst/Cerebro, covering cerebro — agent context, read before touching integrations, project layout, conventions a fresh agent would otherwise miss and running locally.
chessmata CLAUDE.md
Instructions for jonradoff/chessmata, covering chessmata, important guidelines for claude code, example user prompts, project structure and installation.
terragrunt-mcp-server copilot-instructions.md
Instructions for omattsson/terragrunt-mcp-server, covering terragrunt mcp server - ai assistant guide, architecture, key patterns, development and schema drift detection.
ai-primitives-hub CLAUDE.md
Claude Code instructions for AmadeusITGroup/ai-primitives-hub, a project described as: VS Code extension for managing, sharing, and installing AI primitives (Agents, Skills, Prompts, Instructions, MCP) collections for GitHub Copilot and other AI assistants.