A grading tool that applies objective checks to an output and reports whether each check passes or fails. It also creates a grading.json file with the results and reasons.

It is for comparing “with” and “without” cases, recording pass rates, and explaining why individual assertions passed or failed.

It helps separate measurable evaluation from the process that produced the output, while identifying checks that cannot distinguish between two conditions.

grader — Agent for Claude Code by revfactory

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/revfactory/harness-engineering-with-cc

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/grader/github.svg)](https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/grader)

Your own site

<a href="https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/grader"><img src="https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/grader/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/grader"><img src="https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/grader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 163 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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.00163
Opus 5.5	$0.00014	$0.00065
Sonnet 5.5	$0.00007	$0.00033
Haiku 4.5	$0.00004	$0.00016

Measured 2mo ago against content hash c9b8c8c17a96, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

grader 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 2mo 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.

ex-05-11-with-without/.claude/agents/grader.md · 18 lines

What it actually says

grader

output.md에 단언을 적용해 채점한다 (runner와 역할 분리 — 5장 "객관 단언" 정신).

단언 종류

변별력 있는: with PASS / without FAIL이 나와야 좋은 단언 (F4).
변별력 없는(반례): 두 환경 모두 PASS -> non-discriminating, 측정 불가 (F3).

출력

grading.json: {pass_rate, assertions:[{id, desc, result, reason}]}.

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.

2mo ago First seen · 18 lines · 36 tokens per session scan A c9b8c8c17a96

Subscribe to this mod's changes

grader is an agent published in the GitHub repository revfactory/harness-engineering-with-cc (123 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 163 once invoked, about $0.0001 per session on Opus 5.5. 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.

Testing

grader next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
graderrevfactory/harness-engineering-with-cc	Agent	123	5mo ago	Apache-2.0	A	36	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	today	MIT	A	33	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	today	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	today	MIT	A	11	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	today	MIT	A	26	Claude Code

grader

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

grader

단언 종류

출력

What this file has done since we first saw it

grader compared with agents from other repositories