verify-change
Skill958 starsChanged 14 days agoApache-2.0View on GitHub
Verify an existing change against behavioral criteria using tests, reproductions, and explicit evidence gaps. Use when the user asks to check an implementation or invokes /verify-change; report defects without editing implementation or tests.
24 other projects use a version of this.
Adopted by
Most recently taken up by
- developerz-ai/mcp-sshtheir own version, first seen Nov 16, 2026
- chryzxc/hermtheir own version, first seen Nov 15, 2026
- dnsdoctor/claude-plugintheir own version, first seen Nov 8, 2026
- developerz-ai/gold-standards-in-aitheir own version, first seen Nov 8, 2026
- developerz-ai/db-mcp-gatewaytheir own version, first seen Nov 8, 2026
- newkirkjosh/skillstheir own version, first seen Nov 1, 2026
Other versions24 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 24
- ComposioHQ/composio★ 31ksame name
- RLinf/RPent★ 1.8ksame name
- exelearning/exelearning★ 158same name
- liiiiiiiiil/agent-from-scratch★ 93same name
- liiiiiiiiil/coding-agent-from-scratch★ 93same name
- chryzxc/herm★ 45same name
- stoyan-stoyanov/wavefunction★ 20same name
- dativo-io/talon★ 18same name
- augchan42/inkstone★ 5same name
- developerz-ai/db-mcp-gateway★ 5same name
14 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
- plan-changeSkill
- sdk-updateSkill
- security-reviewSkill
- storage-variant-guideSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 20 edited versions we read keep these.
1
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.
- Distinctive: line 21
Run or provide a minimal public-interface reproduction for behavior changes, marking execution status.
“Common” is measured: kept by at least 6 in 10 of the 20 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
Verify a Change
Read AGENT-VERIFICATION.md at the repository root. Follow its shared workflow
contract and section 3's evidence requirements. This is a report-only pass: leave
implementation and tests unchanged, including during specialist reviews.
- Establish the requested diff and revision, including relevant uncommitted files. Reuse agreed criteria and review level. If criteria are absent, infer a short provisional list, label it unconfirmed, and ask the user to confirm intent while continuing independent checks. Ask before proceeding if the scope itself is unclear.
- Map each criterion to actual assertions, existing checks, and relevant specialist evidence. Inspect test content rather than trusting test names or prior summaries.
- Execute relevant supported checks where feasible. Verify the user's edge case, affected variants, and concrete resulting state as applicable. For fixes, gather expected failing-before/passing-after evidence using a non-destructive setup.
- Run or provide a minimal public-interface reproduction for behavior changes, marking execution status. Report absent regression tests or coverage as gaps; do not write tests or fix the implementation during this pass.
Return the shared evidence summary, actionable defects, and pointers to decisions
requiring human inspection. Separate executed evidence from proposed checks and
static test-quality scores. Stop after reporting; fixes belong in implement-change
with agreed criteria. A deeper blind-spot investigation belongs in challenge-change.
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.

