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 skills add openclaw/carapace --skill autoreviewgit clone --depth 1 https://github.com/openclaw/carapaceWrote 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/openclaw/carapace/autoreview)<a href="https://agentmods.dev/skills/openclaw/carapace/autoreview"><img src="https://agentmods.dev/badge/skills/openclaw/carapace/autoreview/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/openclaw/carapace/autoreview"><img src="https://agentmods.dev/badge/skills/openclaw/carapace/autoreview.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.00249 |
| Opus 5.5 | $0.00007 | $0.00100 |
| Sonnet 5.5 | $0.00003 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
autoreview 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 13d 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.
This is a copy
88% identical to autoreview — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Auto Review
Use the canonical autoreview skill.
Read the complete installed ~/.agents/skills/autoreview/SKILL.md and the references
it requires before reviewing. If installed at another operator-selected location,
use that installation. This repository entrypoint contains no review implementation.
If the skill is missing, reuse or clone https://github.com/openclaw/agent-skills
and run python3 scripts/install-skills autoreview from that checkout. On Windows,
use python; --mode copy is available when symlinks are unavailable.
Run the shared scripts/autoreview helper with Python from the repository being
reviewed, preserving its working directory. Follow this repository's review
requirements in addition to the canonical skill.
Keep shared fixes and instructions upstream in openclaw/agent-skills. Update
the shared checkout once for all symlinked consumers; reinstall copy-mode skills
after updating their source. Do not add repository-local helpers or test copies.
What ships with it
7 files 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.
- 13d ago Changed · -389 lines · -3 tokens per session c4a1c7f25403
- 1mo ago First seen · 413 lines · 20 tokens per session scan A 8d92cf5decaf
autoreview is a skill published in the GitHub repository openclaw/carapace (7 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 249 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to autoreview, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
adversarial-review
A multi-stage code review process in which one reviewer looks for failures, another independently checks the findings and the changed code, and a final reviewer decides which findings stand. It requires evidence such as code locations or test results and states that the reviewers may still share the same model's blind spots.
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
redteam-code-audit-detail-pack
Domain routing and boundary guidance for authorized source code security review, including dangerous function tracing, data-flow analysis, logic flaw detection, and dependency review. Use when a task belongs to the code audit domain and needs scope, evidence, pivot, or exit criteria.
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
hero-diff-highlight
A dark code editor reveals a red deletion then a green addition with a soft pulse. Function: PR / code-change explainer.
autoplan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…