agentleFS
kaotyprkaotypr/context-circuit/.agents/skills/cc-review/SKILL.md

cc-review

Skill0 starsChanged 5 days ago0BSDView on GitHub

Run an independent read-only code review of Context Circuit work when a person asks for one, and say so honestly when independence is unavailable.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use .agents/skills/cc-dispatch/SKILL.md to invoke an independent review-capable agent or session when it is requested and available:

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Independent review, on request

Independent verification is a manually requested read-only code review, usually after pull-request creation and optionally after delivery as an audit. It is never triggered by risk classification, and it is not a condition for opening a pull request, delivering, or completing. The one exception is a risk-review override this workspace allowed: when after implement returns it and its instructions say the change warrants review, dispatch the reviewer it names with --override risk-review instead of --review-requested, and report the review with the implementation. .context-circuit/docs/customization.md has the details.

Use .agents/skills/cc-dispatch/SKILL.md to invoke an independent review-capable agent or session when it is requested and available:

sh <root>/.context-circuit/cli --json agent dispatch --host codex --role reviewer --path . --review-requested --task 'Review the billing change against its success criteria'

--review-requested represents the actual user request. It supplies no human approval by itself.

With extensions on, run extension hooks --stage review --when before, with --plan ID where the review is of a plan, before it starts, and --when after once its findings exist.

What to supply

The requested diff, the current revision, relevant surrounding code, and the intent's success criteria. A read-only reviewer cannot run Git on most hosts, so the diff is text you hand it rather than something it fetches.

What a reviewer returns, and does not do

It reports actionable findings with locations and its own limitations. It does not modify code, automatically dispatch fixes, or post external comments unless that was requested. Tests that change files belong to implementation, not to a read-only review.

When independence is unavailable

Explain that limitation and offer an ordinary review instead. Never call the implementing session's own inspection an independent review — a fresh, separate context is the whole point, and reusing the implementer's session produces agreement rather than scrutiny.

The user decides whether to request fixes or proceed. This optional capability does not make child agents mandatory anywhere else.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.