evaluator-write-retest

evaluator-write-retest is a skill for Claude Code from redker56/auto-harness. It costs 35 tokens per session (578 once invoked), scanned A, original, MIT.

An internal evaluation skill for checking fixes again and writing a retest report after a software sprint.

In plain words
What is it for?
Use it inside an evaluator agent to inspect the named fixes, related code, test evidence, and project harness reports. It is not described for general use.
Why use it?
It provides a defined process for verifying that reported fixes actually work and that nearby behavior was not broken.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

Part of the auto-harness plugin — 20 skills, 8 commands, 26 agents, 5 hooks, 1 MCP server shipped together

Good fit Use it inside an evaluator agent to inspect the named fixes, related code, test evidence, and project harness reports. It is not described for general use.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redker56/auto-harness/evaluator-write-retest
Install

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.

Any agent
npx skills add redker56/auto-harness --skill evaluator-write-retest
Clone the repo
git clone --depth 1 https://github.com/redker56/auto-harness

Made for: Claude Code.

Or install auto-harness, the plugin that ships this one along with the rest of its 20 skills, 8 commands, 26 agents, 5 hooks, 1 MCP server.

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.

agentmods badge for evaluator-write-retest

README.md
[![agentmods](https://agentmods.dev/badge/skills/redker56/auto-harness/evaluator-write-retest/github.svg)](https://agentmods.dev/skills/redker56/auto-harness/evaluator-write-retest)
Your own site
<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.

agentmods 80×15 button for evaluator-write-retest

Your own site · 80×15
<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>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 578 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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 0e2dc75501e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

skills/evaluator-write-retest/SKILL.md · 50 lines

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.md when 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.md when 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.md
  • references/templates/retest-report.md
  • references/rubrics/bug-severity.md
  • references/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 Basis to show why the overall Result: PASS | FAIL follows 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.
Files

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.

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.

  1. 9d ago First seen · 50 lines · 35 tokens per session scan A 0e2dc75501e3

Subscribe to this mod's changes

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.

Related

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…

sd0xdev/sd0x-harness · 75 tokens

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…

sd0xdev/sd0x-harness · 70 tokens

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.

sd0xdev/sd0x-harness · 56 tokens

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.

sd0xdev/sd0x-harness · 55 tokens

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…

sd0xdev/sd0x-harness · 95 tokens

precommit

Pre-commit checks — lint:fix -> build -> test.

sd0xdev/sd0x-harness · 15 tokens