eval-curator

eval-curator is an agent for Claude Code from hyhmrright/brooks-lint. It costs 97 tokens per session (805 once invoked), scanned A, original, MIT.

An authoring role for the brooks-lint evaluation suite. An evaluation suite is a set of test scenarios that checks whether a code-review tool detects real problems and avoids false alarms.

In plain words
What is it for?
Adding and maintaining scenarios for code decay and test decay, including expected findings, no-risk cases, health-score cases, and supported review modes.
Why use it?
It keeps new risk rules and skills covered by both matching examples and cases that should not be flagged, while checking that the suite remains valid.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the brooks-lint plugin — 9 skills, 6 commands, 5 agents, 1 hook shipped together

Good fit Adding and maintaining scenarios for code decay and test decay, including expected…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hyhmrright/brooks-lint/eval-curator
About the project

brooks-lint is an AI code-review project that examines software for six kinds of long-term code decay using ideas from twelve classic engineering books. It helps developers review pull requests, audit architecture, assess technical debt, test quality, and apply fixes through structured findings with sources, severity, and remedies. Its catalogue entries provide the skills, commands, agents, instructions, hook, and plugin used to run these reviews.

hyhmrright/brooks-lint · 1,451 stars · on GitHub · hyhmrright.github.io

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.

Clone the repo
git clone --depth 1 https://github.com/hyhmrright/brooks-lint

Made for: Claude Code.

Or install brooks-lint, the plugin that ships this one along with the rest of its 9 skills, 6 commands, 5 agents, 1 hook.

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 eval-curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/hyhmrright/brooks-lint/eval-curator.svg)](https://agentmods.dev/agents/hyhmrright/brooks-lint/eval-curator)
Your own site
<a href="https://agentmods.dev/agents/hyhmrright/brooks-lint/eval-curator"><img src="https://agentmods.dev/badge/agents/hyhmrright/brooks-lint/eval-curator.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 805 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 $0.00097 $0.00805
Opus 5 $0.00048 $0.00402
Sonnet 5 $0.00019 $0.00161
Haiku 4.5 $0.00010 $0.00081

Measured 7d ago against content hash 1b35291d0553, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

eval-curator 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 7d 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.

.claude/agents/eval-curator.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You own evals/evals.json — the benchmark that proves brooks-lint actually fires the right risk codes and, just as important, stays silent where it should.

Core role

  • Append and maintain scenarios in evals/evals.json. Each scenario has id, name, prompt, expected_output, mode, files.
  • Guarantee paired coverage: every risk code (R1–R6, T1–T6) and every skill mode needs ≥1 happy-path scenario (risk code in expected_output) AND ≥1 false-positive scenario flagged no_risk_codes: true.
  • Keep the suite green under npm run evals (structural validation: IDs, fields, risk-code references).

Hard conventions

  1. Sequential id. Append with the next integer id; never reuse or reorder.
  2. Mutually exclusive flags. no_risk_codes: true (no risk codes expected) OR no_health_score: true (Health Score suppression test) — never both.
  3. expected_output is semantic, not verbatim. Describe the Iron Law finding (Symptom + the risk code) and a Health Score range. The evaluator matches meaning. For false-positive / tradeoff scenarios, describe what must NOT appear.
  4. mode must be one of: review, audit, debt, test, health, sweep.

Why false-positive scenarios matter

A suite that only proves "fires on bad code" is half a suite. The expensive failures are over-triggering — flagging a deliberate tradeoff as debt, or firing brooks-debt on an HTTP /health question. A good false-positive scenario is a near-miss: code that superficially resembles the risk but is correct in context. Write the prompt so a naive reviewer would be tempted to flag it, then assert silence.

Input / output protocol

  • Input: from skill-author — which risk codes / skill modes were added or changed. Read the new guide(s) and risk definitions in skills/_shared/ to ground the scenarios in the actual symptom definitions.
  • Output: the appended/edited scenarios, plus a one-line-per-scenario summary (id, mode, risk code or no_risk_codes). Run npm run evals and report the result.

Read the full file on GitHub · 69 lines

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. 7d ago First seen · 69 lines · 97 tokens per session scan A 1b35291d0553

Subscribe to this mod's changes

eval-curator is an agent published in the GitHub repository hyhmrright/brooks-lint (1,451 stars, last pushed 5d ago), licensed MIT. It adds 97 tokens to every session and 805 once invoked, about $0.0005 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 agents, from other repositories

acceptance-test-generator

Generates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal tests with maximum coverage.

shinpr/claude-code-workflows · 68 tokens

quality-fixer-frontend

Specialized agent for verifying React projects and fixing frontend quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, type, or fix requests.

shinpr/claude-code-workflows · 47 tokens

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

shinpr/claude-code-workflows · 44 tokens

integration-test-reviewer

Reviews changed integration and E2E tests against skeletons, proof obligations, or explicit prompt claims. Use after test implementation or when test review/skeleton verification is requested. Returns only material proof gaps with the smallest sufficient corrections.

shinpr/claude-code-workflows · 50 tokens

verifier

Runs a project's configured verification stages (build/unit/integration/etc.) from .lattice/verification.yaml via the deterministic runner script, then returns the run's summary.json verbatim. Invoke before declaring work done, to confirm a change actually works, or whenever a faithful execution report is needed…

techygarg/lattice · 0 tokens

verifier

Mechanical validation on the cheapest tier - runs exactly the commands it is handed, reports exit codes and counts verbatim against the handoff's baseline, and never edits, fixes or theorizes. A red suite is its product, not its failure. Spawned by the conductor at merge time and for the serial re-run of a suspect…

jjanczur/tyran · 71 tokens