evaluator-review-contract

evaluator-review-contract is a skill for Claude Code from redker56/auto-harness. It costs 30 tokens per session (338 once invoked), scanned A, original, MIT.

An internal Auto-Harness skill for evaluator agents reviewing a sprint contract before implementation begins. A sprint contract is the written agreement describing a development sprint’s scope, constraints, and checks.

In plain words
What is it for?
Reading the harness documents and current code, checking whether a sprint is practical and testable, and writing or revising the evaluator review.
Why use it?
It helps catch unclear scope, infeasible work, missing tests, or conflicts with locked project decisions before coding starts.

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 Reading the harness documents and current code, checking whether a sprint is practical and testable, and writing or revising the evaluator review.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/redker56/auto-harness/evaluator-review-contract/github.svg)](https://agentmods.dev/skills/redker56/auto-harness/evaluator-review-contract)
Your own site
<a href="https://agentmods.dev/skills/redker56/auto-harness/evaluator-review-contract"><img src="https://agentmods.dev/badge/skills/redker56/auto-harness/evaluator-review-contract/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-review-contract

Your own site · 80×15
<a href="https://agentmods.dev/skills/redker56/auto-harness/evaluator-review-contract"><img src="https://agentmods.dev/badge/skills/redker56/auto-harness/evaluator-review-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 338 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 $0.00030 $0.00338
Opus 5 $0.00015 $0.00169
Sonnet 5 $0.00006 $0.00068
Haiku 4.5 $0.00003 $0.00034

Measured 11d ago against content hash 844e5bf5ef92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

evaluator-review-contract 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 11d 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-review-contract/SKILL.md · 39 lines

What it actually says

Evaluator Review Contract

This skill governs Evaluator review mode.

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/contracts/sprint-XX-contract.md
  • .harness/contracts/sprint-XX-review.md when revising an existing review.

Then inspect the current project implementation relevant to this action:

  • Read the current source files, routes, components, services, tests, and config that determine whether the proposed sprint contract is feasible and respects locked decisions.
  • Use the codebase to judge feasibility, integration points, and constraint compliance before implementation begins.

Then read these skill references:

  • references/templates/sprint-contract.md
  • references/protocols/file-ownership.md

Follow these rules:

  • Review the sprint contract before implementation begins.
  • Fail the review when scope, testability, verification readiness, or locked decisions are violated.
  • Judge the contract against the written artifacts and the current implementation, not Generator intent.
  • If feasibility or verification cannot be established from the current contract plus the existing codebase, fail conservatively and say why.
  • Cite exact files, boundaries, runtime assumptions, or locked decisions when a hard blocker or revision request is raised.
  • Write only the sprint review artifact.
  • Do not modify application source code or generator-owned artifacts.
Files

What ships with it

2 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. 11d ago First seen · 39 lines · 30 tokens per session scan A 844e5bf5ef92

Subscribe to this mod's changes

evaluator-review-contract is a skill published in the GitHub repository redker56/auto-harness (14 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 338 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

issue-analyze

GitHub Issue and PR review thread deep analysis with Codex blind verdict. Use when: analyzing issue root cause, classifying problems, investigation planning, triaging PR review comments for actionability. Not for: fixing bugs (use bug-fix), code exploration (use code-explore). Output: classified analysis + verdict…

sd0xdev/sd0x-harness · 73 tokens

load-pr-review

Load GitHub PR review comments into AI session — analyze, triage, plan. Default: analysis-only (no auto-fix). Use when: reviewing PR feedback, planning fixes, addressing review comments, replying to reviewers. Not for: creating reviews (use codex-review-fast), creating PRs (use create-pr), viewing PR status (use…

sd0xdev/sd0x-harness · 77 tokens

best-practices

Industry best practices conformance audit with mandatory adversarial debate. Produces audit artifact: verdict (OK/WARN/FAIL) + gap roadmap + debate proof. Use when: auditing current implementation against industry standards, checking compliance with best practices, benchmarking implementation quality, verifying a…

sd0xdev/sd0x-harness · 101 tokens

refactor

Multi-target refactoring orchestrator. Use when: cleaning up messy code/docs, simplifying code, restructuring documents, batch cleanup. Not for: new features (use feature-dev), bug fixes (use bug-fix), code understanding (use code-explore). Output: refactored code/docs + review gate.

sd0xdev/sd0x-harness · 65 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

review-spec

Review technical spec documents from completeness, feasibility, risk, and code consistency perspectives.

sd0xdev/sd0x-harness · 19 tokens