Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/shawnclybor/clybor-claude-toolingnpx agentmods add skills/shawnclybor/clybor-claude-tooling/verifyWrote 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.
[](https://agentmods.dev/skills/shawnclybor/clybor-claude-tooling/verify)<a href="https://agentmods.dev/skills/shawnclybor/clybor-claude-tooling/verify"><img src="https://agentmods.dev/badge/skills/shawnclybor/clybor-claude-tooling/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.
<a href="https://agentmods.dev/skills/shawnclybor/clybor-claude-tooling/verify"><img src="https://agentmods.dev/badge/skills/shawnclybor/clybor-claude-tooling/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00094 | $0.01888 |
| Opus 5.5 | $0.00038 | $0.00755 |
| Sonnet 5.5 | $0.00019 | $0.00378 |
| Haiku 4.5 | $0.00009 | $0.00189 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify
Bridge between "code is written" and "feature is done." Every PRD success criterion must have a corresponding automated or scripted check that returns green. If a criterion can't be verified by a check, either the criterion is wrong (move to open questions) or a check needs to be written.
When to use
- After
ralph-implementcompletes its loop - Before
quality-reviewruns the Stage 6 evaluation - Any time you need to answer "are the PRD criteria actually met?"
When NOT to use
- Mid-implementation (run task-level checks via
ralph-implementinstead) - For non-deterministic criteria — those belong in the evaluation stage, not verification
Inputs
prd_path— path to the PRD with the success criteriacheck_map— mapping of criterion to verification command. Format:<criterion_text>: <command>. Example:P95 latency < 200ms: pytest tests/perf/test_latency.py -k p95.- (optional)
evidence_dir— where to write per-criterion evidence (default.verify/<feature_slug>/)
Output
docs/PRDs/<feature_slug>-verification.md:
# <Feature title> — Verification
**PRD:** [<feature_slug>](./<feature_slug>.md)
**Run at:** <iso8601>
**Verdict:** PASS | FAIL | PARTIAL
## Criteria
| # | Criterion | Check | Result | Evidence |
|---|---|---|---|---|
| 1 | P95 latency < 200ms | `pytest tests/perf/test_latency.py -k p95` | PASS | [run-001.log](../.verify/<slug>/run-001.log) |
| 2 | Returns 400 on invalid email | `pytest tests/api/test_validation.py::test_invalid_email` | PASS | [run-002.log](../.verify/<slug>/run-002.log) |
| 3 | Cyclomatic complexity ≤ 8 in auth/ | `radon cc auth/ -a -nc` | FAIL | [run-003.log](../.verify/<slug>/run-003.log) |
## Failures (if any)
### Criterion 3 — Cyclomatic complexity ≤ 8 in auth/
`auth/token.py:refresh_token` has complexity 11. Top offender: nested conditional in `if not token.valid and not token.expired:`.
**Recommendation:** Extract token validity check into a single boolean predicate.
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.
- 4d ago Changed 48d59c688142
- 1mo ago Changed · +38 lines 0ffcc31164b9
- 1mo ago First seen · 112 lines · 94 tokens per session scan A 194951e7c11e
verify is a skill published in the GitHub repository shawnclybor/clybor-claude-tooling (6 stars, last pushed 5d ago), licensed MIT. It adds 94 tokens to every session and 1,888 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
undo
Revert recent PBR-generated commits by phase/plan, safely using git revert.
suede-ai-eval
Suede AI eval design and coverage audit: AI-SPEC, failure-mode rubric with severity scoring, concrete pass/fail eval cases, coverage and infrastructure scores, and mechanical acceptance gates. Use when a change ships LLM, RAG, agent, classifier, prompt, or generated-media behavior, or when asked to write evals for an…
suede-parity-contract
Suede AI cross-surface canon discipline: hold one canonical answer across every surface that states it (web, iOS, Android, docs, a second service) by generating a contract from the reference surface and making the others assert against it, so a divergence fails a test instead of reaching a user or an answer engine.…
verify
Verify-before-done — exercise the current change end-to-end against its acceptance criteria (the SDD plan's, or the ticket's) and report a per-criterion PASS/FAIL verdict, then record the outcome to memory. This is the concrete action that satisfies moflo's verify-before-done gate (gates.verifybeforedone / /flo -v /…
ward
Ward the codebase — an ad-hoc test-gap audit that reveals unguarded code (untested functions, uncovered edge cases, missing error-handling and integration tests) and conjures ready-to-paste test skeletons as protective wards against regression, surfaced inline in the session. Scoped to your current diff by default, or…
test-gaps
Alias for /ward — see that skill's description.