What is evidence-reviewer?

An evidence-checking guide for comparing completion claims with actual files, requirements, tests, and use. It separates facts such as a file existing from stronger evidence such as a result being tested or viewed.

Use it to map requirements to outputs, choose verification methods, locate evidence, check files and hashes, and review video or audio beyond merely creating it.

It prevents a generated file, template check, or reported measurement from being mistaken for independent quality verification. It also records what remains unverified.

evidence-reviewer — Skill for Claude Code by sodam-ai/SoDam-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.

Any agent

npx skills add sodam-ai/SoDam-Agent --skill evidence-reviewer

Clone the repo

git clone --depth 1 https://github.com/sodam-ai/SoDam-Agent

Made for: Claude Code.

Or install autonomy-team, the plugin that ships this one along with the rest of its 10 skills, 5 hooks.

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/skills/sodam-ai/sodam-agent/evidence-reviewer/github.svg)](https://agentmods.dev/skills/sodam-ai/sodam-agent/evidence-reviewer)

Your own site

<a href="https://agentmods.dev/skills/sodam-ai/sodam-agent/evidence-reviewer"><img src="https://agentmods.dev/badge/skills/sodam-ai/sodam-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sodam-ai/sodam-agent/evidence-reviewer"><img src="https://agentmods.dev/badge/skills/sodam-ai/sodam-agent/evidence-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 181 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	$0.00027	$0.00181
Opus 5.5	$0.00011	$0.00072
Sonnet 5.5	$0.00005	$0.00036
Haiku 4.5	$0.00003	$0.00018

Measured 20d ago against content hash 07f419a0760c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 20d 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.

plugins/autonomy-team/skills/evidence-reviewer/SKILL.md · 11 lines

What it actually says

완료 증거 확인

요구사항→대상→검증 방법→실제 결과→증거 위치→미검증 범위를 연결한다. 파일 존재·해시·문서·테스트·실제 사용을 분리한다. 영상의 생성·디코딩·시청·청취·목적 평가를 구분한다. controller의 evaluate는 템플릿 검사, assess는 보고된 지표 대조이며 독립 품질 검증이 아니다.

사용자·상위 지시와 원본 보존을 우선한다. 현재 권한·도구별 쓰기 게이트를 따르며 내부 관점과 독립 검증을 구분한다.

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.

20d ago First seen · 11 lines · 27 tokens per session scan A 07f419a0760c

Subscribe to this mod's changes

evidence-reviewer is a skill published in the GitHub repository sodam-ai/SoDam-Agent (16 stars, last pushed 20d ago), licensed Apache-2.0. It adds 27 tokens to every session and 181 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 2026-10-21.

Testing agent-team ai-agents cli developer-tools installer

evidence-reviewer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
evidence-reviewersodam-ai/SoDam-Agent	Skill	16	20d ago	Apache-2.0	A	27	Claude Code
kituplathe-cli/kitup	Skill	6	8d ago	Apache-2.0	A	47	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	2d ago	MIT	A	33	Claude Code, Codex
interviewHmbown/CodeWhale	Skill	41k	2d ago	MIT	A	40	Claude Code, Codex
refocusingmvschwarz/openrig	Skill	8.8k	today	Apache-2.0	A	59	Claude Code
atmos-validationcloudposse/atmos	Skill	1.4k	today	Apache-2.0	A	31	Claude Code
gamedev-shadersericrisco/rsc-harness	Skill	573	today	MIT	A	102	Claude Code, Codex