Skip to main content
subagent CX Codex

eval-grader — Claude Code subagent: what it does, how to install

eval-grader — a grader for skill-eval assertions that returns PASS, FAIL or PARTIAL on each, with one line of evidence. Handy when a reviewer's write-up needs a verdict from something that did not produce it.

Elastic-2.0 ★ 155 updated 2026-10-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add serpro69/claude-toolbox
/plugin install kk@claude-toolbox
Open on GitHub

What eval-grader does

Hand it a reviewer's write-up plus a list of assertions and it answers with a verdict on each one: PASS, FAIL or PARTIAL, and a single line pointing at the text that settled it. The agent had no hand in producing what it grades, and it never opens the live fixtures, so the grade cannot quietly drift toward the source of truth.

Component mode is the default. Only the output text counts there, and execution traces do not upgrade a grade. Workflow mode has to be named by the controller: the supplied rubric and manifest load first, sealed evidence after that. An unrecognised mode is an input error, and the agent asks for a corrected one rather than guessing.

Read is the only tool, kept to two jobs: fetching a reviewer-output file the harness left on disk, and re-reading its own agent file or playbook. Paths such as test-files/, klaude-plugin/profiles/** and SKILL.md stay shut, because opening them brings rubric leakage back in. A claim the output text cannot support turns into PARTIAL.

What it helps with

  • Grade a skill eval's assertions one by one
  • Get a verdict from an agent that did not write the output
  • Review a reviewer's text without touching the fixtures
  • Work through a sealed evidence package in workflow mode
  • Spot which behaviour a reviewer's output fails to show

Example prompts for the agent

  • Grade the reviewer output against these assertions and give me PASS, FAIL or PARTIAL for each, with one line of evidence.
  • Grading mode: workflow — load the rubric and manifest first, then open only the evidence files listed there.
  • Check the checklist-loading assertion: if there's no quoted trigger, mark it PARTIAL.

How to install eval-grader

1Plugin marketplace

/plugin marketplace add serpro69/claude-toolbox
/plugin install kk@claude-toolbox

2Manually: put the files in place

.claude/agents/eval-grader.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about eval-grader

How to install eval-grader in Claude Code?

Use the marketplace: /plugin marketplace add serpro69/claude-toolbox, then /plugin install kk@claude-toolbox. The agent file ends up at .claude/agents/eval-grader.md.

What does eval-grader do?

It checks a reviewer's output against the supplied assertions and returns PASS, FAIL or PARTIAL for each, with one line quoting the text or naming what is missing.

How is workflow mode different from component mode?

Component judges the output text alone and traces cannot strengthen the grade. Workflow is turned on by the controller, which makes the rubric and manifest load before any sealed evidence is opened.

Similar subagents

All subagents for Testing and QA →
skill-grader curiositech skill-grader grades Claude Agent Skills on 10 quality axes, assigns letter grades from A+ to F, and lists concrete fixes for each weak axis. Useful when auditing one skill, comparing several, or sweeping a whole library. CX Codex +1 147installs google-agents-cli-eval official Google google-agents-cli-eval runs agent evaluation pipelines, grades responses with LLM judges, and tracks metric failures. Activates during dataset authoring and benchmark runs in agents-cli. CX Codex +1 586,000installs bmad-eval bmad-code-org bmad-eval — a skill for Claude Code, Codex, Cursor and Copilot that runs another skill's test suite and reports findings. Triggers when you need to check description accuracy, compare versions or grade output against a rubric. CX Codex +1 9,100installs eval-harness affaan-m eval-harness — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that brings eval-driven development into every agent session: success criteria go in before any code, results are scored with pass@k and pass^k. CX Codex +1 6,500installs llm-eval-harness daymade llm-eval-harness — a skill for Claude Code, Codex, Cursor, and other platforms that probes a third-party LLM endpoint for availability, speed, system-prompt fidelity, and protocol correctness. CX Codex +1 438installs eval-judge Seth Hobson eval-judge evaluates Claude Code skills across four anchored quality rubrics and returns raw JSON scores from 0.0 to 1.0. CX Codex ★ 42,780repo stars

From the same set30

The whole set →
review-code review-code reviews active git changes through an experienced engineering perspective. Identifies SOLID flaws, architecture issues, and security vulnerabilities. CX Codex +1 ★ 155repo stars review-design review-design is a Claude Code skill that checks design documents before implementation begins. It runs after $kk:design and reviews all documents by default. CX Codex +1 ★ 155repo stars review-spec review-spec is a Claude Code skill that compares code with feature docs and reports mismatches in both directions. Run it mid-feature or after completion. CX Codex +1 ★ 155repo stars design-reviewer design-reviewer audits feature designs and implementation plans without conversational bias. Flags ambiguities, missing edge cases, and contradictions before implementation begins. CX Codex ★ 155repo stars spec-reviewer The spec-reviewer subagent checks code against design documents to find missing work, mismatches, and conflicting or unclear docs. Use it for an independent implementation review. CX Codex ★ 155repo stars code-reviewer code-reviewer is a Claude Code subagent that independently evaluates git diffs for SOLID principles, architectural flaws, and security risks. CX Codex ★ 155repo stars implement This skill guides planned work and standalone fixes through implementation, verification, and code review. It selects a workflow based on the request. CX Codex +1 ★ 155repo stars kk kk — a workflow plugin that carries an AI assistant from design through review, tests and docs, with a permission guard on the side. CX Codex ★ 155repo stars

Project sponsors

Companies that keep this analytics open