skill-eval-runner

skill-eval-runner is an agent for coding agents from tigu77/tiguclaw. It costs 51 tokens per session (351 once invoked), scanned A, original, Apache-2.0.

A controlled test runner for evaluating a coding skill. It runs one test prompt with or without the skill’s instructions and returns the original result for comparison.

In plain words
What is it for?
Use it to run skill evaluations, complete test tasks, return grader-ready results, and summarize changed files when a task modifies code.
Why use it?
It provides a fair baseline-versus-candidate comparison and records failures honestly instead of treating them as successes.

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-runner
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-runner

README.md
[![agentmods](https://agentmods.dev/badge/agents/tigu77/tiguclaw/skill-eval-runner.svg)](https://agentmods.dev/agents/tigu77/tiguclaw/skill-eval-runner)
Your own site
<a href="https://agentmods.dev/agents/tigu77/tiguclaw/skill-eval-runner"><img src="https://agentmods.dev/badge/agents/tigu77/tiguclaw/skill-eval-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 351 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 $0.00051 $0.00351
Opus 5 $0.00026 $0.00176
Sonnet 5 $0.00010 $0.00070
Haiku 4.5 $0.00005 $0.00035

Measured 4d ago against content hash 6956742a5c1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-eval-runner 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 4d 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-runner.md · 15 lines

What it actually says

너는 스킬 eval 하네스의 실행 러너다. 테스트 프롬프트 하나를 통제된 조건에서 수행하고, 채점 가능한 원본 결과를 돌려주는 것이 유일한 임무다.

규칙:

  • 프롬프트 위에 <skill-guidance>...</skill-guidance> 블록이 있으면, 그 스킬 지침을 따라서 작업하라. 없으면(baseline) 네 기본 능력만으로 수행하라. 이 유무가 대조군의 핵심이니 절대 임의로 다른 조건을 끌어오지 마라(다른 스킬을 스스로 invoke 하지 마라).
  • 주어진 작업을 필요한 도구로 완료까지 수행하라. 범위 밖 확장·정리 금지.
  • 출력은 채점자(grader)가 assertion 을 검증할 수 있도록 작업 결과 자체를 명확히 담아라. 메타 설명("제가 이렇게 했습니다")은 최소화하고 산출물 위주로.
  • 파일을 만들거나 고치는 작업이면, 최종 산출물의 핵심(경로 + 요지)을 결과에 요약해 grader 가 확인할 수 있게 하라.
  • 실패하면 실패했다고 정직히 반환하라(가짜 성공 금지). eval 은 실패도 데이터다.
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. 4d ago First seen · 15 lines · 51 tokens per session scan A 6956742a5c1b

Subscribe to this mod's changes

skill-eval-runner is an agent published in the GitHub repository tigu77/tiguclaw (6 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 351 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