agentleFS
bostonaholicbostonaholic/team/skills/team-code-review/SKILL.md

team-code-review

Skill11 starsChanged 3 months agoMITView on GitHub

Use for running the Team code review phase only on explicit request. Never infer from a plain review request. Reviews and fixes the branch.

3 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

10 rules. 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 9

    Distinctive

    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. Distinctive:

    Before each dispatch or retry, read host dispatch and supply its resolved installed paths.

    line 10
  2. Distinctive:

    Before artifact work, read artifact schema.

    line 11
  3. Distinctive:

    Before the tier sort, read finding format.

    line 12
  4. Distinctive:

    Before each consuming step, read its linked shared rules from this installed skill directory.

    line 13
  5. Distinctive:

    If a required read fails, stop that step with the exact path.

    line 14
  6. Distinctive:

    Before finalizing prose you author, read the writing standards.

    line 15
  7. Very specific:

    Write one review-<n>.md per completed round.

    line 20
  8. Distinctive:

    Never: ask the user which Blocking or Major items to address (the no-consult rule).

    line 21
  9. Distinctive:

    Read each reference completely when reaching it, in order.

    line 26
  10. Distinctive:

    Read and apply: execution rules.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Team Code Review

Before each dispatch or retry, read host dispatch and supply its resolved installed paths. Before artifact work, read artifact schema. Before the tier sort, read finding format. Before each consuming step, read its linked shared rules from this installed skill directory. If a required read fails, stop that step with the exact path. Never use checkout fallback or recursive loading. Before finalizing prose you author, read the writing standards. Relay completed reviewer reports unchanged.

Core contracts

  • Require 1-task.md, a non-default branch, at least one commit beyond the merge-base, and a tree clean outside docs/plans/; in multi-repo mode, every worktree 4-repos.md lists.
  • Write one review-<n>.md per completed round; never overwrite a record.
  • Never ask the user which Blocking or Major items to address (the no-consult rule). The loop has no count cap; it ends only when no Blocking or Major finding remains.
  • At PASS, return to the /team phase loop in the same turn when the TodoWrite ledger holds a PR phase item; otherwise print the Next line for /team-security-review. Never load team-security-review or team-pr.

Procedure references

Read each reference completely when reaching it, in order.

  1. Input
  2. Execution

Applied principles

Read and apply: execution rules.

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.