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 commands/elliotbonneville/bareclaw/setupgit clone --depth 1 https://github.com/elliotbonneville/bareclawWrote 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/commands/elliotbonneville/bareclaw/setup)<a href="https://agentmods.dev/commands/elliotbonneville/bareclaw/setup"><img src="https://agentmods.dev/badge/commands/elliotbonneville/bareclaw/setup.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 | $0.00000 | $0.00419 |
| Opus 5 | $0.00000 | $0.00210 |
| Sonnet 5 | $0.00000 | $0.00084 |
| Haiku 4.5 | $0.00000 | $0.00042 |
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 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
Guide the user through setting up their BAREclaw instance. This is a first-run setup flow.
Steps
1. Check prerequisites
Verify that the .env file exists and has the required variables configured:
BARECLAW_TELEGRAM_TOKEN(if they want Telegram)BARECLAW_ALLOWED_USERS(required for Telegram)BARECLAW_HTTP_TOKEN(recommended for HTTP auth)
If .env doesn't exist, copy .env.example and walk them through filling it in.
2. Personalize SOUL.md
Read the existing SOUL.md — it defines your core personality and engineering principles. Ask the user if they want to add a personal section at the top. Things to ask about:
- Name: Do they want to call you something specific?
- Tone adjustments: More casual? More technical? Different from the defaults?
- Boundaries: Things you should never do without asking (e.g., git push, delete files, deploy to prod)
- Context: What they're working on, what kind of tasks they'll typically send you
If they want changes, add a ## Personal section near the top of SOUL.md with their preferences. Don't overwrite the existing personality or engineering principles — those are the project defaults.
If they're happy with the defaults, move on.
3. Install heartbeat
Run bash heartbeat/install.sh to set up the heartbeat scheduled job. Confirm it installed successfully.
4. Start the server
If not already running, start with npm run dev. Verify it starts successfully.
5. Test connectivity
If Telegram is configured, send a test message via POST /send to confirm the bot can reach them.
Important
- Be conversational during setup — this is the user's first impression of their agent.
- Don't dump all questions at once. Ask them one topic at a time.
- If they seem impatient, offer to use sensible defaults and let them customize later.
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 · 38 lines · 0 tokens per session scan A e5ffc50009ae
setup is a command published in the GitHub repository elliotbonneville/bareclaw (22 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 419 tokens. 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.