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 sd0xdev/sd0x-harness --skill verifygit clone --depth 1 https://github.com/sd0xdev/sd0x-harnessWrote 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/sd0xdev/sd0x-harness/verify)<a href="https://agentmods.dev/skills/sd0xdev/sd0x-harness/verify"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/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/sd0xdev/sd0x-harness/verify"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00017 | $0.01405 |
| Opus 5.5 | $0.00007 | $0.00562 |
| Sonnet 5.5 | $0.00003 | $0.00281 |
| Haiku 4.5 | $0.00002 | $0.00140 |
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 16d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Loop
Trigger
- Keywords: verify, run tests, check, lint, typecheck, verification
When NOT to Use
- Pre-commit gate (use
/precommitor/precommit-fast) - Test coverage review (use
/codex-test-review) - Running a single specific test (run directly)
Commit Context
Claude Code 2.1.286 and later tell Claude to run a skill named verify before a commit. The gate
that binds a commit is /precommit (rules/auto-loop.md), so when /verify runs as that
pre-commit check it neither repeats a precommit that already passed nor stands in for one that did
not:
- Read the gate state:
node scripts/review-state.js check --format=json, installed copy first (.claude/scripts/review-state.js). precommit.passedis exactlytrue→ report "Precommit already passed at the current code digest; no new checks executed" and stop. Emit no sentinel and write no verdict note.- Anything else —
passedfalse, noprecommitslot, output that does not parse as JSON, or no checker found → run/precommit. Its own report and evidence contract apply;/verifyadds no verdict of its own.
passed is content-addressed — noted, at the current tree digest, with verdict pass — so no
separate freshness check is needed. Run any other way, /verify performs the steps below unchanged.
Workflow Steps
| Step | Goal | Safety | Skip if Missing |
|---|---|---|---|
| lint | Check code style (read-only) | read-only | yes |
| typecheck | Static type checking (full only) | read-only | yes |
| test-unit | Run unit test suite | read-only | yes |
| test-integration | Run integration tests (full only) | read-only | yes |
| test-e2e | Run end-to-end tests (full only) | read-only | yes |
Failure behavior: continue-all (run all steps, report all results)
Task
Step 1: Check for runner script
Use Glob to check if .claude/scripts/verify-runner.js exists in the project root.
- Found → run:
node .claude/scripts/verify-runner.js $ARGUMENTS- If runner succeeds, use its output and skip to the Output section.
- If runner fails, treat as a real verification failure (do not silently fallback).
- NOT found → skip to Step 2 (do NOT attempt to run the runner).
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.
- 16d ago Changed · +22 lines 51a612a65894
- 1mo ago First seen · 114 lines · 17 tokens per session scan A ee4a9acf7a66
verify is a skill published in the GitHub repository sd0xdev/sd0x-harness (194 stars, last pushed 12d ago), licensed MIT. It adds 17 tokens to every session and 1,405 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
testing-setup
Analyze and create a testing strategy for Android apps - install testing libraries, set up test infrastructure, create harnesses for unit tests, UI tests, screenshot tests, and end-to-end tests.
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
building
Use when writing production code test-first: the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns.
testing-assistant
Manages testing lifecycle including unit tests, integration tests, validation, and quality assurance.
langchain4j-testing-strategies
Provides unit test, integration test, and mock AI patterns for LangChain4j applications. Creates mock LLM responses, tests retrieval chains, validates RAG workflows, and implements Testcontainers-based integration tests for Java AI services. Use when unit testing AI services, integration testing LangChain4j…
testing-strategies
Comprehensive testing strategy covering unit, integration, e2e, property-based, and mutation testing with practical patterns.