Borrowing it
Nothing to install: this file belongs to mathaix/OpenClawMachines. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mathaix/OpenClawMachines/main/.agents/skills/ocm-review/SKILL.mdgit clone --depth 1 https://github.com/mathaix/OpenClawMachinesWrote 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/skills/mathaix/openclawmachines/ocm-review)<a href="https://agentmods.dev/skills/mathaix/openclawmachines/ocm-review"><img src="https://agentmods.dev/badge/skills/mathaix/openclawmachines/ocm-review.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 5.1 | $0.00029 | $0.00548 |
| Opus 5 | $0.00015 | $0.00274 |
| Sonnet 5 | $0.00006 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
ocm-review 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 8d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OCM Review
Use this skill for PR review, review-comment resolution, post-fix review, or any request asking whether a change is correct, safe, or the best fix.
Review Posture
Review behavior, not prose. A convincing PR description is not proof. Read the real code path, adjacent tests, docs, and deployment assumptions before giving a verdict.
Required Pass
- State what the change does and why the surface matters.
- Read the changed files plus enough surrounding code to identify:
- runtime entry point
- owner module
- one caller
- one callee
- sibling surfaces that should share the invariant
- adjacent tests
- relevant config/docs
- Compare with current
origin/mainbehavior when regression or compatibility matters. - For dependency-backed behavior, read official docs/source/types instead of relying on memory.
- Decide whether the patch is the best owner-boundary fix or only a plausible mitigation.
- Require focused proof for bug fixes: reproduction/log/failing test when practical, root cause in code, fix touching the implicated path, and a regression test or explicit reason no test was added.
OCM-Specific Checks
- Local/operator paths must not depend on hosted-only Cloudflare, GCP, Firebase, or private-domain defaults.
- Every VM path must preserve the gateway/proxy token and signing-key contract.
- Worker origins must not point back at hostnames served by the same Worker route.
- User-facing machine access must go through the configured data-plane protection model; do not expose KVM worker hosts directly.
- Host enrollment must keep workers authenticated as infrastructure, not human users.
- Runtime/rootfs changes need guest-init and agent-client compatibility checks.
- Public-core changes must not add billing, commercial plan enforcement, or private hosted overlay assumptions.
Output Shape
Use this compact structure:
Findings:ordered by severity with file/line references.Best-fix verdict:best / acceptable mitigation / wrong layer / too narrow / too broad.Alternatives considered:one to three concrete alternatives and why they were rejected.Code read:main files/contracts inspected.Proof:tests, logs, or commands checked.Remaining uncertainty:what was not proven.
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.
- 8d ago First seen · 68 lines · 29 tokens per session scan A 493c3e0e9179
ocm-review is a skill published in the GitHub repository mathaix/OpenClawMachines (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 548 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
harness-loop
The §5 autonomous-improvement-loop procedure specialized to this harness's own reviewer prompts (agents/code-reviewer.md + agents/security-reviewer.md) — the mission-specific 9-step regulation layered on skills/loop's generic mechanics. NOT for an arbitrary mission (use /loop for that), and NOT for editing…
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.
prs-awaiting-maintainer
List open pull requests where the ball is in the maintainer's court: CI is green and the PR is ready for a maintainer to review, re-review, or merge. Use when the user wants to see PRs awaiting maintainer action.
compliance-checker
Check affiliate content for FTC compliance and platform rules. Triggers on: "check my content for compliance", "FTC disclosure check", "is this legal", "review for compliance", "check affiliate disclosure", "am I FTC compliant", "audit my content", "compliance review", "legal check", "platform rules check", "check…