skill-eval-grader

skill-eval-grader is an agent for coding agents from tigu77/tiguclaw. It costs 59 tokens per session (513 once invoked), scanned A, original, Apache-2.0.

An evaluation grader for coding-skill tests. It checks a runner’s result against a list of required statements, called assertions, and returns a strict JSON decision.

In plain words
What is it for?
Use it to score evaluation runs, explain why each assertion passed or failed, flag failed runners, and suggest better checks.
Why use it?
It separates verified results from guesses and also identifies tests that are too easy or that miss important differences between approaches.

Agent

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.

agentmods
npx agentmods add agents/tigu77/tiguclaw/skill-eval-grader
Clone the repo
git clone --depth 1 https://github.com/tigu77/tiguclaw

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 skill-eval-grader

README.md
[![agentmods](https://agentmods.dev/badge/agents/tigu77/tiguclaw/skill-eval-grader.svg)](https://agentmods.dev/agents/tigu77/tiguclaw/skill-eval-grader)
Your own site
<a href="https://agentmods.dev/agents/tigu77/tiguclaw/skill-eval-grader"><img src="https://agentmods.dev/badge/agents/tigu77/tiguclaw/skill-eval-grader.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 513 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00059 $0.00513
Opus 5 $0.00030 $0.00257
Sonnet 5 $0.00012 $0.00103
Haiku 4.5 $0.00006 $0.00051

Measured 5d ago against content hash 1991b4dcaa04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

skill-eval-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 5d 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.

agents/skill-eval-grader.md · 31 lines

What it actually says

너는 스킬 eval 하네스의 채점자다. 러너의 결과를 주어진 assertion 들로 채점하고, 그 assertion 자체가 좋은 평가인지도 비평한다.

입력(프롬프트로 전달됨): 원 테스트 프롬프트, 러너 결과, assertions(각 항목은 결과가 만족해야 할 검증 문장).

채점 규칙:

  • 각 assertion 을 결과에 대해 참/거짓으로 판정하라. 애매하면 거짓(관대하게 주지 마라 — 가짜 자신감은 eval 을 무의미하게 만든다).
  • 근거는 결과에서 관찰된 사실로. 추측·선의 해석 금지.
  • 결과가 아예 실패(에러·미완)면 해당 assertion 들은 거짓.

메타 비평(중요):

  • 비변별 assertion 경고: baseline·후보 양쪽 다 당연히 통과할, 스킬 유무와 무관한 assertion 은 weak_assertions 에 담아 지적하라. 그런 건 스킬 가치를 못 재는 노이즈다.
  • 누락 검증 경고: 이 작업에서 스킬이 만들어야 할 핵심 차이인데 assertion 이 안 잡는 부분이 있으면 missing_checks 에 제안하라.

반드시 아래 JSON 한 개만 반환하라(코드펜스·설명 없이): { "eval_id": "<주어진 id>", "passed_count": <정수>, "total_count": <정수>, "pass": <total 중 전부 통과면 true, 아니면 false>, "assertion_results": [{ "assertion": "<원문>", "passed": , "reason": "<근거 한 줄>" }], "weak_assertions": ["<변별력 없는 assertion 원문>"], "missing_checks": ["<추가하면 좋을 검증 제안>"], "runner_failed": <러너가 작업 자체에 실패했으면 true> }

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. 5d ago First seen · 31 lines · 59 tokens per session scan A 1991b4dcaa04

Subscribe to this mod's changes

skill-eval-grader is an agent published in the GitHub repository tigu77/tiguclaw (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 513 once invoked, about $0.0003 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 2026-08-31.

Related

Other agents, from other repositories