Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add smartwhale8/claude-playbook --skill verifygit clone --depth 1 https://github.com/smartwhale8/claude-playbookWrote 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/smartwhale8/claude-playbook/verify)<a href="https://agentmods.dev/skills/smartwhale8/claude-playbook/verify"><img src="https://agentmods.dev/badge/skills/smartwhale8/claude-playbook/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/smartwhale8/claude-playbook/verify"><img src="https://agentmods.dev/badge/skills/smartwhale8/claude-playbook/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 | $0.00040 | $0.00488 |
| Opus 5.5 | $0.00016 | $0.00195 |
| Sonnet 5.5 | $0.00008 | $0.00098 |
| Haiku 4.5 | $0.00004 | $0.00049 |
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 1mo 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.
What it actually says
Verify the change
What to verify, if the user said: $ARGUMENTS
Claude stops when the work looks done. "Looks done" is not evidence. This skill produces evidence.
Run the checks
Run each command the project defines, in this order, and stop at the first failure to fix it before continuing. The commands come from .claude/CLAUDE.md. If they are not recorded there, find them in package.json, Makefile, pyproject.toml, or the CI workflow, and then add them to CLAUDE.md so the next session does not repeat this search.
- Type check. The compiler catches what the tests miss.
- Lint. Never suppress a rule to get a pass.
- Tests. The full suite, not only the file you touched. A change that passes its own test and breaks two others is not done.
- Build. The build succeeding is a separate fact from the tests passing.
Behavioural check
Running the suite proves the tests pass. It does not prove the change does what was asked. Add one check that exercises the actual behaviour:
- An API change: call the endpoint and show the request and the response.
- A UI change: run the app, take a screenshot, and compare it with what was asked for.
- A command-line change: run the command and show its output.
- A data change: query the result and show the rows.
Report
State the outcome first: verified, or not verified.
Then the evidence, as a short table of each command and its result, followed by the output of anything that failed.
Rules for this report:
- Paste what the commands returned. Never summarize a pass you did not see.
- A skipped check is reported as skipped, with the reason. Never as a pass.
- If the suite was already failing before this change, say so and name the failures that are pre-existing.
- Do not claim success while any check is red.
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.
- 1mo ago First seen · 44 lines · 40 tokens per session scan A d3ff582aa9ba
verify is a skill published in the GitHub repository smartwhale8/claude-playbook (43 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 488 once invoked, about $0.0002 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 2026-09-21.
Other skills, from other repositories
ring:running-dev-cycle
Running the backend dev cycle: implements every task in a rolling-wave plan.md (ring:writing-plans format) for a Go/TS service, driving specialist agents through Gate 0 implementation/TDD, Gate 8 parallel review, and Gate 9 validation per epic, elaborating later phases at each phase boundary. Use when starting or…
ring:instrumenting-streaming-events
Instrumenting streaming events: wires lib-streaming event emission end-to-end into a Lerian Go service via a 13-gate cycle (catalog, Builder bootstrap, Emit sites, outbox, HTTP manifest, NoopEmitter fallback, integration and chaos tests), dispatching ring:backend-go under TDD. Consumes the validated…
ring:implementing-tasks
Implementing a single planned task (Task N.M.T) end-to-end: selects the right backend agent by language and service type, drives one TDD RED->GREEN turn, then verifies coverage, lint, license headers, runtime, and delivery before handoff. Runs as Gate 0 before ring:reviewing-code. Use to drive ONE task inside an…
ring:writing-skills
Writing or editing a Ring skill: SKILL.md structure, frontmatter and Agent-Search-Optimization rules, token-efficiency targets, and bulletproofing (Iron Law, rationalization tables, Red Flags) so discipline-enforcing skills resist excuses. Use when creating or revising a skill. Delegates pressure-testing to…
ring:adding-multi-tenancy
Adding database-per-tenant isolation into a Go service end-to-end via an 11-gate cycle: detects the stack, audits compliance, then dispatches backend agents to implement tenantId-from-JWT routing through the lib-commons v5 dispatch layer (config, middleware, repositories, metrics, tests) and runs reviewers. Use when…
ring:test-driven-development
Enforcing the RED-GREEN-REFACTOR loop: write one failing test and watch it fail, write minimal code to pass, then refactor green. Use when starting implementation of a new feature or bugfix, or writing any new production code. Requires pasted failure output as proof of RED; code written before its test must be…