setup

A setup procedure for ChessClaw, a Codex-based assistant that can chat through Telegram. It installs dependencies, checks Apple's container runtime on macOS, configures authentication, and starts the service.

In plain words
What is it for?
Use it to install ChessClaw, connect a Telegram bot, choose subscription or API-key authentication, discover the chat, and launch its background service.
Why use it?
It turns several first-time setup tasks into an ordered checklist and pauses when a user must provide access or complete an external step.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fmbenhassine/chessclaw/setup
Any agent
npx skills add fmbenhassine/chessclaw --skill setup
Clone the repo
git clone --depth 1 https://github.com/fmbenhassine/chessclaw

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 403fe9f1bbb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.codex/skills/setup/SKILL.md · 237 lines

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:

  1. Codex login/subscription (recommended)
  2. 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.

  1. Open Telegram and search for @BotFather
  2. Send /newbot
  3. Choose a bot name
  4. Choose a bot username ending in bot
  5. 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.

Read the full file on GitHub · 237 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 237 lines · 32 tokens per session scan A 403fe9f1bbb6

Subscribe to this mod's changes

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.