A pre-commit and pre-pull-request check that runs the same sequence as the repository's CI job. CI, or continuous integration, automatically checks proposed changes; these checks include static analysis, tests, race detection, formatting, and linting.

Use it to check whether changes are ready to commit or submit as a pull request.

It finds failures locally before they block a pull request or reach the shared build system. Running the checks in the documented order also stops at the first problem, making failures easier to address.

How luthersystems/elps configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to luthersystems/elps. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/luthersystems/elps/main/.claude/skills/verify/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/luthersystems/elps

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/luthersystems/elps/verify/github.svg)](https://agentmods.dev/skills/luthersystems/elps/verify)

Your own site

<a href="https://agentmods.dev/skills/luthersystems/elps/verify"><img src="https://agentmods.dev/badge/skills/luthersystems/elps/verify/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/luthersystems/elps/verify"><img src="https://agentmods.dev/badge/skills/luthersystems/elps/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,267 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01267
Opus 5.5	$0.00000	$0.00507
Sonnet 5.5	$0.00000	$0.00253
Haiku 4.5	$0.00000	$0.00127

Measured 2d ago against content hash b6a717af9f67, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/verify/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/verify — CI Gate Skill

Runs the same checks as the Lint & Test job in .github/workflows/elps.yml, in the same order. Use it before committing or creating a PR. If CI's steps change, update this file to match — the workflow is the authority.

Trigger

Use when asked to verify changes, check CI readiness, or as a pre-commit/pre-PR gate.

Pipeline

Run in order. Stop and report on the first failure.

#	Step	Command	CI step name
1	Confidentiality guard	`bash scripts/confidentiality-guard.sh`	Confidentiality guard
2	Go static checks	`make static-checks`	golangci-lint, golangci-lint config schema
3	Tests	`make test`	Tests
4	Race detector	`make race`	Race detection (full)
5	Tagged tests	`make test-elpscheck`	Singleton integrity (elpscheck)
6	elps's own Go analyzers	`make elpsvet`	Seal contract (elpsvet)
7	Sealed-AST benchmark oracle	`make bench-elpscheck-smoke`	Sealed-AST oracle over the benchmarks
8	Format	`go build -o elps . && ./elps fmt -l ./...`	Check formatting
9	Lisp lint	`./elps lint --workspace=. --exclude 'grammar' --include '_examples' ./...`	Lint ELPS source
10	Docstrings	`./elps doc -m`	Check missing documentation
11	API break gate	`make api-break-gate` (`BASE=origin/main` default)	API break gate (job `api-break`)
12	Work marker gate	(none: shared workflow)	`quality / result` (job `work-markers` in the shared Quality workflow)

Notes:

Step 2: make static-checks runs golangci-lint config verify, then golangci-lint run ./..., then a second pass under --build-tags elpscheck scoped to ./lisp/... (tagged files are invisible to the first, and today they only live there). It warns when your golangci-lint differs from CI's pin; on a mismatch, trust CI — see "golangci-lint version skew" in AGENTS.md before deleting any //nolint.
Step 6: two passes (untagged and GOFLAGS=-tags=elpscheck). For interpreting a finding, use the /elpsvet skill.
Step 8: -l lists files that would change; fix with ./elps fmt ./... and re-run.
Step 9: fix the diagnostic, or add ; nolint:<check-name> only for a genuine false positive.
Step 10: add the missing docstring to the builtin/op/macro/export.
Step 11: fails when the branch removes or incompatibly changes the Go API of a non-internal package or the Lisp public surface (packages, exports, kind, formals) against its merge base with BASE. If the break is intended, paste the line the gate prints into scripts/api-breaks.txt, fill the issue (and the substrate migration) and reason, and justify it in the PR. Otherwise restore compatibility (keep the old name/arity, add instead of change).
Step 12: fails on a work marker that does not name an open issue (MARKER(#N)) and that .github/quality/work-markers.txt does not cover, and on an entry that covers nothing. Do the work, or name its issue. Delete stale entries.
CI also builds and vets on Windows (go build ./... && go vet ./...); run go vet ./... if you touched OS-specific code.
Touched scripts/, cmd/benchgate, benchmark.yml or fuzz.yml? Also run make ci-gates-test (and make fuzz-classify-test for fuzz changes).

Read the full file on GitHub · 83 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 83 lines · 0 tokens per session scan A b6a717af9f67

Subscribe to this mod's changes

verify is a skill published in the GitHub repository luthersystems/elps (36 stars, last pushed today), licensed BSD-3-Clause. It costs nothing until one of its globs matches a file; then it loads 1,267 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.

Code review Go Testing embedded-language go lisp

code-guidelines-go

Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…

dimetron/pi-go · 124 tokens

vhs-e2e-gif

Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…

dimetron/pi-go · 106 tokens

ci-orchestrator

Run a CI-like pipeline locally (format, lint, vet, static-analysis, tests) and summarize per-step results with remediation guidance.

pilinux/gorest · 32 tokens

code-review-pi

Review code for quality, run linters, check test coverage, fix issues, and enforce gates. Save the final report to ./specs/issues/003-code-review-pi/PROMPT.md. Use before committing changes.

dimetron/pi-go · 50 tokens

bmad-checkpoint-preview

LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".

mmornati/leanproxy-mcp · 49 tokens

go-127

What changed in Go 1.27 (released August 2026) and how it changes the way Go is written in pi-go. Use this skill when writing or reviewing Go that could use a 1.27 feature, when bumping the go directive in go.mod, when a build or test behaves differently after a toolchain upgrade, or when code-guidelines-go points…

dimetron/pi-go · 177 tokens

elps: Skill for Claude Code