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/mathaix/openclawmachines/readmegit clone --depth 1 https://github.com/mathaix/OpenClawMachinesWhat 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 | $0.00584 |
| Opus 5 | $0.00000 | $0.00292 |
| Sonnet 5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
README 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code slash commands
Project slash commands for working on OpenClaw Machines. In Claude Code, type
/<name> (e.g. /test) and the agent follows the steps in the matching
.claude/commands/<name>.md file. Adapted from the internal monorepo and
sanitized for this repo (the private Cloud Run / GCS deploy commands are
intentionally omitted — see below).
Available commands
| Command | What it does |
|---|---|
/start |
Start the control plane (:8080) and frontend (:5173) via scripts/local-dev.sh (Postgres + env + migrations). |
/stop |
Stop the dev servers (and optionally the Docker Postgres / local Firecracker worker). |
/status |
Health-check the control plane + frontend (make status). |
/test |
Run the test suite — make test (Go + frontend), or individual test-go / test-unit / test-frontend / typecheck. |
/verify |
Full quality gate before committing: make check (vet/lint/vuln/shellcheck) → make test-go → make typecheck. |
/pr |
Commit, push, and open a PR with a generated summary + test plan. |
/currentfeature |
Archive the current feature doc, bump RELEASE.md, and start a fresh branch from main. |
/codex |
Delegate a review or read-only task to the OpenAI Codex CLI (codex review / codex exec). Requires the codex CLI. |
/freshclone |
Make a clean clone of the repo (backs up the current dir) after corrupted/conflicted state. |
Intentionally omitted (private deploy pipeline)
These exist in the internal monorepo but were left out because they drive infrastructure that isn't part of this repo (the Make targets don't exist here):
/deploy—make deploy-all(Cloud Run / Cloudflare)./snapshot—make build-components/upload-agent(build + upload artifacts to GCS)./versions—gsutil cat gs://openclawmachines/...(deployed artifact versions).
For local Firecracker provisioning instead, see scripts/local-e2e-firecracker.sh
and docs/local-firecracker-e2e.md.
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 · 40 lines · 0 tokens per session scan A 87fa2949216c
README is a command published in the GitHub repository mathaix/OpenClawMachines (57 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 584 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
stop
Gracefully stop a running Bernstein orchestration.
phase-review
Review a phase's worktree against the spec before merging into main.
riskreview
The user invoked the /riskreview facade command from the risk-review-pipeline pack.
tech-debt
Run bun run check:fix and then bunx knip and identify unused files and functions to refactor the project and simplify. Look at the deprecated features and confirm with the user to delete them. Look at the dependencies and remove the ones that are not needed based on knip results.
publish-core
Trigger the canonical publish pipelines in this repo.
scriptwriter-draw
Draw a random chaos card from the 13-card deck — a plot-twist prompt the user can use as a scene seed, a basistext for an RRR cascade, or a riff for a room contribution.