agentleFS
amirbenaamirbena/code-review-skill/skills/review-deep-investigation/SKILL.md

review-deep-investigation

Skill8 starsChanged 8 days agoApache-2.0View on GitHub

Lifts review-core's investigation bound with multi-hop tracing, root cause, affected tests and failure and null paths. Use when a suspicion needs more than one hop to settle.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Read-only, by review-core's S1 and S10.

    line 23
  2. Distinctive:

    Read in full before step 1.

    line 29
  3. Distinctive:

    Report what was traced: Add the "Investigation" section to the report after "Findings", and remove from "Not investigated" every concern …

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

review-deep-investigation

Lifts review-core's investigation bound for the suspicions it could not settle in one hop. It adds findings and a list of what it traced. It never changes severity, the decision rule, the REVIEW INCOMPLETE triggers or S1–S5 and S10; those are review-core's.

Requires review-core. Install it alongside this Skill; without it, stop and ask the user to install it.

Entry contract

  • Runs only after review-core has run on the same target in this run, and only when selected under review-core's "Mode" (S6, stated there): from the request, on a yes to the Core's ask, or on evidence in auto.
  • Needs no input beyond the target and the Core's findings and "Not investigated" concerns.
  • Read-only, by review-core's S1 and S10. It uses Git and grep only: git grep, git log -S/-G, git show, git blame, and file reads. It builds no graph, index, AST or cache, and runs no project code.

Files

Read in full before step 1.

  • rules/investigation.md — the investigation types and how far tracing goes.

Procedure

  1. Collect the open questions: the Core's "Not investigated" concerns marked beyond the bound, plus any suspicion from reading the change that one hop does not settle.
  2. Investigate each under rules/investigation.md. Stop each one on confirm or dismiss.
  3. Add the findings. A confirmed defect is a finding in review-core's shape and severity scale, deduplicated with the Core's findings by root cause. A dismissed suspicion adds nothing.
  4. Report what was traced. Add the "Investigation" section to the report after "Findings", and remove from "Not investigated" every concern this run settled.

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.