agent-run-evidence-reviewer

agent-run-evidence-reviewer is a skill for Claude Code, Codex from 45ck/skill-harness. It costs 33 tokens per session (259 once invoked), scanned A, original, MIT.

A review checklist for agent run traces, evaluation summaries, tool logs, and handoff records. It decides whether the evidence is strong enough to accept a result or store a learning.

In plain words
What is it for?
Use it to review completed runs, workflow improvements, self-improvement proposals, redaction needs, missing validation, and follow-up issues.
Why use it?
It prevents claims of success from being accepted without named changes, tests, failures, and other supporting evidence. It also flags sensitive traces and unfinished work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review completed runs, workflow improvements, self-improvement proposals, redaction needs, missing validation, and follow-up issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/45ck/skill-harness/agent-run-evidence-reviewer
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.

Any agent
npx skills add 45ck/skill-harness --skill agent-run-evidence-reviewer
Clone the repo
git clone --depth 1 https://github.com/45ck/skill-harness

Made for: Claude Code, Codex.

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 agent-run-evidence-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/45ck/skill-harness/agent-run-evidence-reviewer/github.svg)](https://agentmods.dev/skills/45ck/skill-harness/agent-run-evidence-reviewer)
Your own site
<a href="https://agentmods.dev/skills/45ck/skill-harness/agent-run-evidence-reviewer"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/agent-run-evidence-reviewer/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.

agentmods 80×15 button for agent-run-evidence-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/45ck/skill-harness/agent-run-evidence-reviewer"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/agent-run-evidence-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 259 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 $0.00033 $0.00259
Opus 5 $0.00016 $0.00130
Sonnet 5 $0.00007 $0.00052
Haiku 4.5 $0.00003 $0.00026

Measured 11d ago against content hash ee4ec84357ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-run-evidence-reviewer 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 11d 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.

packs/agent-operating-skills/skills/agent-run-evidence-reviewer/SKILL.md · 37 lines

What it actually says

Agent Run Evidence Reviewer

Use this skill before accepting that an agent run worked, that a workflow improved, or that a learning should be made durable.

Evidence Checks

  • The run has a task or issue id.
  • The agent role and tool boundaries are clear.
  • Changed files, commands, tests, and validators are named.
  • Failures and retries are visible, not edited out.
  • Claims are tied to concrete evidence.
  • Generated artifacts point back to source.
  • Sensitive traces are excluded or redacted.
  • Follow-up work is filed instead of hidden in prose.

Verdicts

  • accept: evidence supports the result
  • needs-gate: result may be correct but validation is missing
  • needs-redaction: evidence is useful but unsafe to store or share
  • needs-follow-up: result is partial and requires tracked work
  • reject: evidence contradicts the result or is too weak

Output

Verdict

Evidence Present

Missing Gates

Redaction Needs

Follow-Up Issues

Durable Learning Decision

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. 11d ago First seen · 37 lines · 33 tokens per session scan A ee4ec84357ce

Subscribe to this mod's changes

agent-run-evidence-reviewer is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 259 once invoked, about $0.0002 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.