agentleFS
itsofficialadiitsofficialadi/boundiff/.agents/skills/surgical-change/SKILL.md

surgical-change

Skill0 starsChanged 25 days agoMITView on GitHub

Implement a small feature or bounded bug fix with minimal files and a focused diff. Use for scoped implementation; not for broad redesigns, read-only reviews, or release operations.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Inspect: Read the entry point, affected implementation, nearby tests, and project-specific instructions.

    line 14
  2. Distinctive:

    Implement: Follow existing conventions.

    line 17
  3. Distinctive:

    Verify: Run the smallest useful checks first, then nearby checks if practical.

    line 18
  4. Distinctive:

    Do not stage, commit, push, release, deploy, or mutate external systems unless explicitly authorized.

    line 24
  5. Distinctive:

    Do not update dependencies or regenerate large artifacts just because a tool suggests it.

    line 25
  6. Distinctive:

    Remove only dead code/imports caused by this change unless broader cleanup was requested.

    line 26
  7. Distinctive:

    Do not claim an outcome is verified when checks were skipped, failed, or only simulated.

    line 27

≈ “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

Surgical change

Objective

Deliver the requested behavior with the narrowest correct modification and explicit verification. This workflow implements code; it is not an independent review.

Steps

  1. Inspect. Read the entry point, affected implementation, nearby tests, and project-specific instructions. Confirm what is already working.
  2. Bound the task. State a one-sentence outcome and a small set of observable acceptance criteria. Identify in-scope files and explicit exclusions when useful.
  3. Handle uncertainty. Choose and disclose a narrow reversible assumption for harmless ambiguity. Stop before a decision affecting security, production, external authority, credentials, data loss, or irreversible state.
  4. Implement. Follow existing conventions. Prefer direct changes over additional layers, configuration, or dependencies. Keep unrelated code untouched.
  5. Verify. Run the smallest useful checks first, then nearby checks if practical. For a bug, prefer evidence of prior failure and subsequent success when available.
  6. Inspect. Review changed paths and full diff for incidental changes, weakened validation, or unexplained formatting. Check worktree state.
  7. Report. Summarize behavior changed, verification evidence, test gaps, assumptions, and unrelated observations without fixing them opportunistically.

Boundaries

  • Do not stage, commit, push, release, deploy, or mutate external systems unless explicitly authorized.
  • Do not update dependencies or regenerate large artifacts just because a tool suggests it; explain necessity before expanding scope.
  • Remove only dead code/imports caused by this change unless broader cleanup was requested.
  • Do not claim an outcome is verified when checks were skipped, failed, or only simulated.

Output

A concise handoff with scope, change, evidence, and limitations. Cite actual commands/results where available; never invent passing tests.

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.