verify-change
Skill2 starsChanged yesterdayMITView on GitHub
Prove a change in developerz-ai/gold-standards-in-ai before committing or opening a pull request — the repo's own install, run and check commands. Use before every commit.
24 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- developerz-ai/mcp-sshedited, first seen Nov 16, 2026
- chryzxc/hermtheir own version, first seen Nov 15, 2026
- Apicurio/apicurio-registrytheir own version, first seen Nov 9, 2026
- dnsdoctor/claude-plugintheir own version, first seen Nov 8, 2026
- developerz-ai/db-mcp-gatewayedited, 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 · 2
- developerz-ai/db-mcp-gateway★ 519% same
- developerz-ai/mcp-ssh★ 249% same
Wrote their own version · 22
- ComposioHQ/composio★ 31ksame name
- RLinf/RPent★ 1.8ksame name
- Apicurio/apicurio-registry★ 958same 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
12 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 repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- plan-slicesSkill
- stale-claimsSkill
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 24
Run every command from the repo root — the scripts cd there themselves.
- Distinctive: line 45
Add the test that fails first, then the fix — a green run that never went red proves nothing.
“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 in developerz-ai/gold-standards-in-ai
House skill — owned by this repository's maintainers from this repo’s own detected commands. Correct it in place; setup never overwrites a skill that exists.
The one gate
bin/check is the gate. CI runs it and the pre-commit hook runs it, so a change that
passes it locally passes everywhere.
| Step | Command | What it is |
| install | bin/setup | echo "gold-standards-in-ai: markdown only, no dependencies to install" |
| run | bin/dev | echo "gold-standards-in-ai: no app to run - read README.md for the map" — on developerz.ai runs, start it with code_bash_background when you need a running stack |
| prove | bin/check | runs bin/check-docs (index + relative-link + #fragment validation) then bin/test (its regression fixtures); silent on success. Exits 0 when the change passes, 75 when a gate precondition is unmet, any other nonzero for a validation or regression failure. The real gate is bin/check-docs — run it, never copy its slug rules |
| stop | bin/stop | true — on developerz.ai runs, the platform runs this when your session ends — do not stop the stack yourself |
Rules
- Run every command from the repo root — the scripts
cdthere themselves. bin/checkred is not a pull request. Fix the cause, never silence the gate.- The gate's rules live in
bin/check-docs; read them there instead of copying them:- a doc under
docs/needs the rootREADME.mdand its sectionREADME.mdto carry it; - a
#fragmentis the slug of the target's heading — lowercase, every character that is not a letter, a digit,-or_deleted, spaces turned into-.## ⌨️ Keyboard pathsis-keyboard-paths;## 6. Merge → deploy without a human bottleneckis6-merge--deploy-without-a-human-bottleneck.
- a doc under
Exit codes bin/check uses
A coding box runs this gate before it commits, and it has to tell a FAILING change from a gate it could not run — otherwise correct work is thrown away as if it were red. Exit 1 cannot carry that difference, so one code is reserved:
| Exit | Means | What the platform does |
| 0 | the change passes | commit it |
| 75 | a gate precondition is unmet — the gate could not grade | refuse the commit, and blame the environment, never the change |
| any other non-zero | validation or regression failed — the gate ran and the change is red | refuse the commit, and blame the change |
- Guard preconditions FIRST and
exit 75when one is unmet.exit 1there tells the platform your change is broken when it is your environment that is. - Changed a dependency? Re-run
bin/setupbeforebin/check, or you are proving a stale tree. - Add the test that fails first, then the fix — a green run that never went red proves nothing.
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.

