AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Surgical Changes

skill-developersglobal-ai-agent-skills-surgical-changes · by DevelopersGlobal

Enforces minimal code modifications — touch only what you must. Prevents drive-by refactoring, comment deletions, and style changes unrelated to the task.

No reviews yet
0 installs
37 views
0.0% view→install

Install

$ agentstack add skill-developersglobal-ai-agent-skills-surgical-changes

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-developersglobal-ai-agent-skills-surgical-changes)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Surgical Changes? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Overview

Every changed line is a line the reviewer must inspect, a line that could introduce a regression, and a line that will appear in the git blame forever. Unnecessary changes are costly.

AI agents often "improve" adjacent code, reformat files, rename variables for consistency, or delete "dead" code — all without being asked. This creates noisy diffs, unexpected behavior changes, and broken trust.

This skill enforces a hard rule: every changed line must trace directly to the user's request.

When to Use

  • Any time you are modifying existing code (not creating new files)
  • When your diff is larger than you expected
  • When reviewing your own generated changes before presenting them

Process

Step 1: Establish the Change Boundary

  1. Read the task carefully. Write down exactly which files and functions need to change.
  2. Draw a mental boundary: "Everything outside this boundary is out of scope."
  3. List what you will NOT change, even if you'd do it differently:
  • Adjacent functions
  • Variable naming conventions
  • Comment style
  • Import order
  • Formatting/whitespace (unless fixing a specific bug)

Verify: You can name the specific functions/lines that need to change.

Step 2: Make Only the Required Changes

  1. Make the changes — and only the changes — within the defined boundary.
  2. If you notice something wrong outside the boundary:
  • Mention it in a comment — don't fix it silently
  • Example: "Note: I noticed fetchUser has no error handling, but I'm leaving that for a separate PR."
  1. If your changes made imports/variables/functions unused: remove only those created by YOUR changes. Leave pre-existing dead code alone (unless asked).

Verify: No line changed that wasn't part of the defined scope.

Step 3: Review Your Own Diff

  1. Read through your diff line by line.
  2. For each changed line, ask: "Why did I change this?"
  • If you can't answer → revert it
  1. Flag any changes that are purely cosmetic and ask: "Should I include this?"

Verify: Every changed line has a clear reason directly tied to the task.

Step 4: Document Scope Decisions

  1. In your PR/commit message, explicitly note what you chose NOT to change and why:
  • "Did not refactor the adjacent parseDate function — out of scope for this fix."

Common Rationalizations (and Rebuttals)

| Excuse | Rebuttal | |--------|----------| | "I improved it while I was there" | That's a separate PR. Drive-by improvements hide bugs and inflate diffs. | | "The old comment was wrong" | Fix comments related to your change. Leave others for a documentation PR. | | "I made the code more consistent" | Consistency PRs should be standalone. Don't bundle them. | | "It's just whitespace" | Whitespace changes cause merge conflicts and obscure real diffs in blame. | | "The dead code is obviously wrong" | File an issue. Don't delete pre-existing code without explicit approval. |

Red Flags

  • Your diff is 3× larger than the feature size suggests
  • You changed files that aren't related to the task
  • You reformatted a file "while you were there"
  • You renamed variables for consistency
  • You deleted comments or code you didn't fully understand
  • Your PR description says "and also fixed a few other things"

Verification

  • [ ] Every changed line traces to the task description
  • [ ] No cosmetic-only changes bundled in (or explicitly approved)
  • [ ] Pre-existing dead code left untouched (or flagged, not deleted)
  • [ ] Changes to adjacent unrelated code: zero
  • [ ] Diff size is proportional to task size

References

  • [simplicity-first skill](../simplicity-first/SKILL.md)
  • [code-review skill](../code-review/SKILL.md)
  • Karpathy: "They still sometimes change/remove comments and code they don't sufficiently understand as side effects, even if orthogonal to the task."

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.