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 redker56/auto-harness --skill evaluator-write-retestgit clone --depth 1 https://github.com/redker56/auto-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/redker56/auto-harness/evaluator-write-retest)<a href="https://agentmods.dev/skills/redker56/auto-harness/evaluator-write-retest"><img src="https://agentmods.dev/badge/skills/redker56/auto-harness/evaluator-write-retest/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/redker56/auto-harness/evaluator-write-retest"><img src="https://agentmods.dev/badge/skills/redker56/auto-harness/evaluator-write-retest.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 | $0.00035 | $0.00578 |
| Opus 5 | $0.00017 | $0.00289 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
evaluator-write-retest 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 9d 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
Evaluator Write Retest
This skill governs Evaluator retest mode and the sprint retest report.
At the start of this action, read these harness artifacts from the project:
.harness/status.md.harness/intake.md.harness/spec.md.harness/design-direction.md.harness/runtime.md.harness/contracts/sprint-XX-contract.md.harness/contracts/sprint-XX-review.mdwhen a review exists for the sprint..harness/qa/sprint-XX-qa-report.md.harness/qa/sprint-XX-fix-log.md.harness/qa/sprint-XX-retest.mdwhen rewriting the retest report.
Then inspect the current project implementation relevant to this action:
- Read the source files, routes, components, services, tests, and config touched by the named fixes and the nearby regression surface.
- Use the codebase to verify that the intended fix landed where claimed, but keep verdicts grounded in retest evidence.
Then read these skill references:
references/protocols/file-ownership.mdreferences/templates/retest-report.mdreferences/rubrics/bug-severity.mdreferences/rubrics/retest-review.md
Follow these rules:
- Retest only the named fixes and tightly related regression surface.
- Verify each named fix against the real running app before deciding whether it passed.
- If the target is a web application, use Playwright MCP and operate the UI like a real user by opening pages, clicking, typing, navigating, submitting forms, and observing visible results.
- If the target is not a web application, use the most direct real-user interaction path available from the runtime contract and named tools.
- Use the retest template exactly.
- Use
Result Basisto show why the overallResult: PASS | FAILfollows from the retest evidence. - Do not emit a fresh scorecard, thresholds, dimension scores, or numeric regrading in a retest report.
- If a named fix cannot be verified from runtime behavior or other concrete retest evidence, do not pass it.
- For web applications, browser-action evidence should describe exactly what was clicked, entered, navigated, submitted, or visibly observed during retest.
- Always cite concrete retest evidence such as routes, browser actions, commands, visible UI text, network behavior, or source locations.
- Do not silently upgrade unresolved issues to passed status.
- Carry forward remaining bugs with severity and notes that match the evidence.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 50 lines · 35 tokens per session scan A 0e2dc75501e3
evaluator-write-retest is a skill published in the GitHub repository redker56/auto-harness (14 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 578 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
feature-verify
Feature verification (READ-ONLY, P0-P5). Use when: verifying feature behavior after deployment, validating API responses, diagnosing production issues, post-deploy smoke test. Not for: modifying data (use feature-dev), code review (use codex-review-fast), writing tests (use codex-test-gen), security audit (use…
test-health
Holistic test coverage measurement. Use when: assessing test health, measuring coverage trends, quantitative + qualitative test audit. Not for: running tests (use verify), reviewing test sufficiency only (use codex-test-review), generating tests (use codex-test-gen). Output: multi-dimensional dashboard with coverage…
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
post-dev-test
Post-development test completion. Use when: checking test coverage after feature-dev, writing missing integration/e2e tests. Not for: unit test generation (use codex-test-gen), test review (use test-review). Output: test files + coverage report.
pre-pr-audit
Pre-PR confidence audit with 5-dimension scoring. Use when: final check before commit/push/PR, evaluating PR readiness, assessing test quality + risk + coverage holistically. Triggers: pre-pr, readiness check, confidence audit, final verification, ready to PR, how confident. Not for: code review (use…
precommit
Pre-commit checks — lint:fix -> build -> test.