verify-change
Skill18 starsChanged 24 days agoApache-2.0View on GitHub
Run the right local verification ladder for a Talon change, map every CI job to its local command, and reproduce a CI failure from a pasted log before changing anything.
- Reads credentials
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
- Apicurio/apicurio-registrytheir own version, first seen Nov 9, 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
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★ 1.7ksame name
- Apicurio/apicurio-registry★ 951same name
- exelearning/exelearning★ 153same name
- liiiiiiiiil/agent-from-scratch★ 93same name
- liiiiiiiiil/coding-agent-from-scratch★ 93same name
- chryzxc/herm★ 45same name
- stoyan-stoyanov/wavefunction★ 20same 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 repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- architecture-reviewSkill
- cut-releaseSkill
- implement-issueSkill
- investigate-bugSkill
- prepare-prSkill
- respond-to-reviewSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 1 is distinctive, and 5 are 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.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 6
Verify $ARGUMENTS (a change, a package set, or a pasted CI log).
- Very specific: line 10
Run narrow first, broad before handoff, one heavyweight suite at a time (the dev hosts have few cores.
- Very specific: line 22
Use -count=1 for anything you will report.
- Very specific: line 55
Read the Run <command> header line: it names the job step and therefore the row above.
- Very specific: line 57
Run the step's exact command locally, with the same flags (-race, -tags, -count=1), on the whole package, not only the failing test.
- Very specific: line 65
No sleeps, retries, or fixture-specific branches to hide a failure (see .claude/rules/testing.md).
“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 $ARGUMENTS (a change, a package set, or a pasted CI log).
Ladder
Run narrow first, broad before handoff, one heavyweight suite at a time (the dev hosts have few cores; never run two race/integration/e2e suites concurrently).
- Focused:
go test ./internal/<pkg> -run '<TestName>' -count=1 - Package(s) touched, with the race detector:
go test -race -count=1 ./internal/<pkg>/... - Black-box tiers the change crosses:
- integration:
go test -race -count=1 -tags=integration ./tests/integration/... - e2e (builds the binary in TestMain):
go test -count=1 -tags=e2e -timeout 5m ./tests/e2e/... - offline smoke sections:
SMOKE_ONLY="37_mcp_governance 38_openshell 39_budget" make test-smoke(no provider key); the fullmake test-smokeneedsTALON_SECRETS_KEYandOPENAI_API_KEY.
- integration:
- Static:
gofmt -l .,go vet ./...,golangci-lint run ./...,git ls-files -z '*.sh' | xargs -0 shellcheck,git diff --check. - Repository guards whenever docs, examples or templates changed:
go test ./tests(vocabulary and architecture-claim guards) andbash scripts/check-claim-discipline.sh. - Repository-level confidence:
make check(lint, vet, SSOT gate, unit, integration, guards) andmake test-e2e.
Use -count=1 for anything you will report. Report exactly which commands ran and their result; name what you did not run and why.
CI job to local command
| Workflow / job / step | Local equivalent | Needs |
| CI / test / Format check, Vet | gofmt -l ., go vet ./... | — |
| CI / test / Run unit tests | go test -race -count=1 $(go list ./internal/... ./cmd/... | grep -v internal/testutil | grep -v internal/llm/testutil | grep -v 'cmd/talon') | CGO + SQLite |
| CI / test / PII benchmark regression | make benchmark-regression | linux/amd64 for the baseline |
| CI / test / Run integration tests | go test -race -count=1 -tags=integration ./tests/integration/... | — |
| CI / test / Run repository guard tests | go test ./tests | — |
| CI / test / Run e2e tests | go test -count=1 -tags=e2e -timeout 5m ./tests/e2e/... | — |
| CI / test / MCP governance smoke | make test-mcp-governance-smoke | — |
| CI / test / OpenShell composition smoke | make test-openshell-smoke | — (fixture supervisor, no Docker) |
| CI / test / OpenShell showcase runner contract | make test-openshell-showcase-contract | — |
| CI / test / Check coverage | unit coverage ≥ 65% (coverage.out from the unit run) | — |
| CI / test / Conformance count | make conformance | — |
| CI / test / OPA/Rego policy tests | make opa-test | opa binary |
| CI / proof-gates | make proof-gates (fuzz gates; slow) | — |
| CI / product-demo-smoke | make smoke-product-demo | gum; writes under /tmp (copy the script and redirect paths on a host where /tmp is read-only) |
| CI / lint, shellcheck | golangci-lint run ./..., shellcheck over git ls-files '*.sh' | — |
| CI / build, docker | make build, docker build -t talon:ci . | Docker for the image |
| Docs / Markdown link check, claim discipline | check every link you added by hand; bash scripts/check-claim-discipline.sh | — |
| Security / govulncheck, gitleaks, SBOM | govulncheck ./... when go.mod or the toolchain changes | network |
| Shortlist Demo | make verify-shortlist-demo | Docker compose |
| OpenShell Live / live (v0.1.3 required, v0.1.4 experimental) | make test-openshell-live (OPENSHELL_VERSION=v0.1.x) | Docker ≥ 28 on Linux, GHCR pull |
| OpenShell Live / showcase | make openshell-showcase-validate | Docker ≥ 28 on Linux |
| CodeQL | no local equivalent | — |
Anything in the Docker rows cannot be proven on a host without a Docker socket; say so and let the PR's own CI run be the proof for those rows.
Reproducing a CI failure from a log
- Read the
Run <command>header line: it names the job step and therefore the row above. - Establish which commit CI ran before concluding anything:
gh pr view <n> --json headRefOid(or the GitHub API) againstgit log -1. A failure is often already fixed by a local commit that has not been pushed; say that instead of re-fixing. - Run the step's exact command locally, with the same flags (
-race,-tags,-count=1), on the whole package, not only the failing test. - If it passes in isolation but fails in the package run, look for order or environment dependence: shared global state, cwd-relative files, pricing fixtures (black-box fixtures use the real catalog, where
ollamais zero-cost), time boundaries, a pre-existing recovered panic printed by another test. Do not call it flaky until you have a mechanism. - A fix needs a test that fails without it; re-run the step's full command afterwards and quote the result.
Fixture rules that CI enforces
- Black-box fixtures (
internal/server,tests/integration,tests/e2e) price with the production estimator over the embedded catalog. A provider or model outsidepricing/models.yamlis deniedpricing_unavailablein tests exactly as in production; fix the fixture's provider or model, never the estimator. - Preventive claims are proven by counting the upstream or action target, not by a status code.
- No sleeps, retries, or fixture-specific branches to hide a failure (see
.claude/rules/testing.md).
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.

