plan-change
Skill958 starsChanged 14 days agoApache-2.0View on GitHub
Plan an agent-assisted change with behavioral acceptance criteria, review depth, and a verification plan. Use before implementation when the user requests planning or invokes /plan-implementation.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- CsHeng/agent-skillstheir own version, first seen Nov 9, 2026
- 0xdeafcafe/skillstheir own version, first seen Nov 6, 2026
- aantoniadis/skillstheir own version, first seen Oct 20, 2026
- matheusPavaneli/workbenchtheir own version, first seen Oct 20, 2026
- Ionate-Technologies/indium-agentkittheir own version, first seen Oct 20, 2026
- otaviobarros/agent-engineeringtheir own version, first seen Oct 17, 2026
Used with
Projects with it also use review-change.
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.
thlaureSkillreview-change
Use this skill when the user asks for a code review, a correctness pass, a check before PR, or asks whether a Signalist change follows project conventions.
Also in 7 projects that use this
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- Indium-AI-Labs/indium-agentkit★ 18same name
- Ionate-Technologies/indium-agentkit★ 17same name
- CsHeng/agent-skills★ 3same name
- otaviobarros/agent-engineering★ 3same name
- contextosai/skills★ 1same name
- hamburger-os/PraxFlow★ 1same name
- matheusPavaneli/workbench★ 1same name
- 0xdeafcafe/skills★ 0same name
- aantoniadis/skills★ 0same name
- BanKnight/claude-template★ 0same name
1 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 repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- apicurio-test-qualitySkill
- challenge-changeSkill
- implement-changeSkill
- sdk-updateSkill
- security-reviewSkill
- storage-variant-guideSkill
- verify-changeSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
0
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
- Very specific: line 8
Read AGENT-VERIFICATION.md at the repository root.
“Common” is measured: kept by at least 6 in 10 of the 10 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
Plan a Change
Read AGENT-VERIFICATION.md at the repository root. Follow its shared workflow
contract and sections 1–2. This skill plans only; leave implementation and tests unchanged.
- Establish the task from the request and conversation. Ask if the goal is unclear.
- Inspect relevant code, repository instructions, and existing tests. Identify applicable specialist guidance using the shared contract; use it for planning, not for regeneration, automatic fixes, or full test-quality detector sweeps.
- Reuse agreed criteria. Propose at most five observable input/outcome criteria, preserved behavior, assumptions, and unresolved questions.
- Choose the review level by consequence of failure. Map each criterion to meaningful checks, including existing coverage and affected variants/contracts.
- For fixes, plan expected failing-before/passing-after regression evidence. For behavior changes, plan a public-interface reproduction. Identify critical decisions needing human inspection and likely verification blockers.
Return the concise plan and ask the user to confirm intent and provide an independent
edge case. Stop before implementation. Do not require another approval when the
same criteria and plan have already been approved. The next step is
/implement-changes, not an automatic transition to editing.
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.

