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 skills/fmbenhassine/chessclaw/setupnpx skills add fmbenhassine/chessclaw --skill setupgit clone --depth 1 https://github.com/fmbenhassine/chessclawWhat 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 | $0.00032 | $0.01435 |
| Opus 5 | $0.00016 | $0.00718 |
| Sonnet 5 | $0.00006 | $0.00287 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
setup 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChessClaw Setup (Codex)
Run commands directly. Pause only when user action is required (Telegram bot setup, chat discovery, runtime install, auth choice).
1. Install Dependencies
npm install
2. Confirm Apple Container Runtime
echo "Platform: $(uname -s)"
which container && echo "Apple Container: installed" || echo "Apple Container: not installed"
If the platform is not macOS, stop and tell the user this base setup flow targets Apple Container on macOS.
If Apple Container is missing, ask user to install from:
Then verify:
container system start
container --version
3. Configure Codex Authentication
Ask user which path they want:
- Codex login/subscription (recommended)
- API key in
.env
Option A: Codex login/subscription
Tell user to run in another terminal:
codex login
Then proceed. ChessClaw will copy host ~/.codex/auth.json into the assistant session directory automatically.
Option B: API key
Create .env with one of:
echo 'OPENAI_API_KEY=' > .env
# or
echo 'CODEX_API_KEY=' > .env
Optional overrides (only if needed):
cat >> .env << 'EOF_ENV'
OPENAI_BASE_URL=
OPENAI_ORG_ID=
OPENAI_PROJECT_ID=
EOF_ENV
Validate:
grep -E '^(OPENAI_API_KEY|CODEX_API_KEY)=' .env || echo "No key configured"
4. Build Container Image
./container/build.sh
Smoke test:
echo '{}' | container run -i --entrypoint /bin/echo chessclaw-agent:latest "Container OK"
5. Create Telegram Bot
Tell the user:
I need a Telegram bot token for ChessClaw.
- Open Telegram and search for
@BotFather- Send
/newbot- Choose a bot name
- Choose a bot username ending in
bot- Copy the bot token
Wait for the token before continuing.
6. Configure Assistant Chat
- ChessClaw uses exactly one Telegram chat as the assistant channel.
- The expected setup is a direct private chat between the user and the bot.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 237 lines · 32 tokens per session scan A 403fe9f1bbb6
setup is a skill published in the GitHub repository fmbenhassine/chessclaw (5 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,435 once invoked, about $0.0002 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 skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
agent-collective-intelligence-coordinator
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator.
agent-orchestrator-task
Agent skill for orchestrator-task - invoke with $agent-orchestrator-task.
agent-payments
Agent skill for payments - invoke with $agent-payments.
add-resend
Add Resend (email) channel integration via Chat SDK.
add-macos-statusbar
Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.