Index of every page on this site: llms.txt
All skills
openclaw avatar

/autoreview

@7b51dc8
by openclawopenclaw/clawscan156 stars
30
Run it yourself

Structured code review through the shared OpenClaw agent-skills installation.

Use this Skill: https://skilld.dev/gh/openclaw/clawscan/autoreview

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈22 tokens for metadata: the name and description. ≈672 when used: this file.

Description uses 1.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈90 characters, or 1.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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.

For this repository, default to GPT-6.1 Sol with high reasoning and Standard service. Preserve an explicit user-selected engine, model, effort, or service tier. The example below is only for an otherwise-unconfigured Codex route. CLI flags override environment defaults; do not blindly append these flags when a user or operator has selected another value. Apply defaults independently:

  • Engine: honor an explicit user choice or AUTOREVIEW_ENGINE; otherwise Codex.
  • Model: omit the repository --model default when an explicit choice, AUTOREVIEW_CODEX_MODEL, or AUTOREVIEW_MODEL selects it.
  • Effort: omit the repository --thinking default when an explicit choice, AUTOREVIEW_CODEX_THINKING, AUTOREVIEW_THINKING, or an explicit Codex model_reasoning_effort config override selects it.
  • Tier: omit --codex-speed default when an explicit speed/tier choice, AUTOREVIEW_CODEX_SPEED, or a service_tier override in --codex-config / AUTOREVIEW_CODEX_CONFIG selects it. Preserve that explicit override.

Pass user-selected CLI values as requested; otherwise omit the corresponding flag so the helper can read its supported environment/config setting. Add only missing Codex defaults. For a non-Codex engine, do not project Codex-specific model/effort/tier defaults onto it.

With no such choices or environment overrides, run:

python3 "$HOME/.agents/skills/autoreview/scripts/autoreview" \
  --engine codex --model gpt-6.1-sol --thinking high --codex-speed default \
  --max-priority P3 --mode local

Use --mode branch --base origin/main for the committed branch review.

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.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The 'autoreview' skill is a security-focused code review tool that uses engines like Codex and Claude to analyze code diffs. It features a sophisticated defense-in-depth architecture, including automated detection of hardcoded secrets, environment isolation for subprocesses, and strict scope controls to prevent the agent from performing unauthorized actions. No malicious behaviors or data exfiltration vectors were identified.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

Signed by skilld at 7b51dc8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated last month

README badge

README badge for openclaw/clawscan/autoreview