safe-refactor
Skill1 starsChanged 2 months agoMITView on GitHub
Plan and execute one small behavior-preserving refactor phase with local dependency mapping, compatibility, rollback, validation, and commit boundaries. Use for approved extractions, module splits, dependency untangling, or test migration. Do not use to generate a broad architecture inventory, redesign UX or behavior, add features, update docs only, or create commits.
26 other projects use a version of this.
Adopted by
Most recently taken up by
- sudeepgupta90/my-ai-marketplacetheir own version, first seen Nov 8, 2026
- mjlueck-hash/cavemantheir own version, first seen Nov 8, 2026
- dhruvsaxena1998/skillstheir own version, first seen Nov 8, 2026
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
- pahlevikun/levistacktheir own version, first seen Nov 1, 2026
- Terryc21/sitreptheir own version, first seen Nov 1, 2026
Used with
Projects with it also use verify-and-stop, investigate-first and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JuliusBrusseeSkillverify-and-stop
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
Also in 8 projects that use this
JuliusBrusseeSkillinvestigate-first
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
Also in 7 projects that use this
- +10 more from JuliusBrussee
Other versions26 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 26
- JuliusBrussee/caveman★ 118ksame name
- Terryc21/sitrep★ 50same name
- JPeetz/agent-skills★ 14same name
- yeaight7/agent-powerups★ 6same name
- dfedoryshchev/weftworks★ 5same name
- Linchi1997yeh/craftsman-suite★ 2same name
- nomdedev/agent-manager-template★ 2same name
- xingtu1996/dsh-xingtu-skills★ 2same name
- dennisrongo/claude-skills★ 1same name
- dhruvsaxena1998/skills★ 1same name
16 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- architecture-auditSkill
- commit-reviewSkill
- cxpSkill
- docs-updateSkill
- session-handoffSkill
- task-briefSkill
- cxpSkill
The file
We split this skill into the rules it gives an agent
12 rules. 0 are common, 11 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 24 edited versions we read keep these.
11
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
- Distinctive: line 15
Use after the refactor scope and behavior contract are approved.
- Very specific: line 21
Do not use to discover the whole architecture, redesign product behavior, make visual changes, implement unrelated cleanup, or prepare …
- Distinctive: line 45
Run the scope-appropriate validation ladder and inspect the complete diff.
- Distinctive: line 59
Do not combine architecture movement with UX changes or speculative cleanup.
- Distinctive: line 60
Do not let parallel agents edit the same working tree.
- Distinctive: line 61
Do not hide failures or alter unrelated code to make validation pass.
- Distinctive: line 62
Do not claim browser behavior from unit tests or Streamlit AppTests alone.
- Distinctive: line 63
Do not stage, commit, push, reset, discard, or delete compatibility paths without explicit authorization.
- Distinctive: line 68
Follow the task-specific ladder in AGENTS.md, starting with focused tests.
- Distinctive: line 69
Verify compatibility before removing an old import, path, or test boundary.
- Distinctive: line 70
Keep automated, manual, browser, and provider evidence distinct.
- Distinctive: line 71
Stop the phase when required validation fails and report the blocker.
“Common” is measured: kept by at least 6 in 10 of the 24 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.
Files
Safe Refactor
Purpose
Move one coherent responsibility while preserving observable behavior and keeping rollback straightforward.
Trigger
Use after the refactor scope and behavior contract are approved. Use an existing architecture audit when the change crosses boundaries or the dependency map is not already known.
Do not trigger
Do not use to discover the whole architecture, redesign product behavior, make
visual changes, implement unrelated cleanup, or prepare commits. Use
architecture-audit first when a broad inventory is still required.
Inputs
- Approved objective, phase, file scope, and non-goals.
- Current behavior contract and compatibility constraints.
- Relevant architecture/dependency evidence.
- Characterization or regression tests and required manual checks.
- Validation ladder and rollback point.
Workflow
- Confirm branch state, approved scope, protected areas, and current behavior.
- Map only the dependencies touched by this phase; do not expand into a new architecture audit.
- Capture invariants, including Streamlit rerun, callback, widget identity, and session-state semantics when applicable.
- Define one extraction boundary and its temporary compatibility mechanism.
- Move the smallest coherent responsibility without UX, schema, provider, persistence, or domain changes outside the approved task.
- Move or add tests with the behavior they protect; retain characterization coverage until the new boundary is proven.
- Run the scope-appropriate validation ladder and inspect the complete diff.
- Report rollback instructions and logical commit boundaries. Do not stage or commit without separate authorization.
Outputs
Return the implemented phase, preserved behavior, compatibility path, tests, validation evidence, risks, rollback point, and commit boundary. Use the refactor phase checklist for multi-step work.
Safety
- Preserve behavior unless the approved task explicitly changes it.
- Do not combine architecture movement with UX changes or speculative cleanup.
- Do not let parallel agents edit the same working tree.
- Do not hide failures or alter unrelated code to make validation pass.
- Do not claim browser behavior from unit tests or Streamlit AppTests alone.
- Do not stage, commit, push, reset, discard, or delete compatibility paths without explicit authorization.
Validation
- Follow the task-specific ladder in
AGENTS.md, starting with focused tests. - Verify compatibility before removing an old import, path, or test boundary.
- Keep automated, manual, browser, and provider evidence distinct.
- Stop the phase when required validation fails and report the blocker.
- Review staged scope later with
commit-reviewwhen requested.
References
AGENTS.md— behavior, Git, and validation rules.architecture-audit— broad inventory that must precede this skill when dependencies are not known.- Refactor phase checklist — phase contract and rollback format.
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
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.

