evidence-collector

evidence-collector is an agent for Claude Code from malakhov-dmitrii/forge. It costs 29 tokens per session (710 once invoked), scanned A, original, MIT.

An independent verification agent that checks every acceptance criterion in a FINAL-PLAN.md file. It runs checks itself and reports whether each criterion passes or fails.

In plain words
What is it for?
Reviewing implementation plans, running fresh tests or commands for each criterion, identifying weak or vague criteria, and reporting failed verification so the work can be corrected.
Why use it?
It reduces reliance on an implementer's claims or old logs when deciding whether planned work is actually complete.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the beast-forge plugin — 3 skills, 2 commands, 17 agents, 3 hooks shipped together

Good fit Reviewing implementation plans, running fresh tests or commands for each criterion, identifying weak or vague criteria, and reporting failed verification so the work can be corrected.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/malakhov-dmitrii/forge/evidence-collector
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/malakhov-dmitrii/forge

Made for: Claude Code.

Or install beast-forge, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 17 agents, 3 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.

agentmods badge for evidence-collector

README.md
[![agentmods](https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/evidence-collector/github.svg)](https://agentmods.dev/agents/malakhov-dmitrii/forge/evidence-collector)
Your own site
<a href="https://agentmods.dev/agents/malakhov-dmitrii/forge/evidence-collector"><img src="https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/evidence-collector/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 evidence-collector

Your own site · 80×15
<a href="https://agentmods.dev/agents/malakhov-dmitrii/forge/evidence-collector"><img src="https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/evidence-collector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00029 $0.00710
Opus 5 $0.00015 $0.00355
Sonnet 5 $0.00006 $0.00142
Haiku 4.5 $0.00003 $0.00071

Measured 10d ago against content hash 9c90f642318f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

evidence-collector scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Run the command chain from the plan (curl, query, etc.).
agents/evidence-collector.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evidence Collector

You are an independent evidence collector. You have NEVER seen the executor's work. Your ONLY input is the FINAL-PLAN.md file.

Karpathy Guardrails (Goal-Driven Execution)

A criterion is only useful if passing it means the feature actually works.

  • "Should work" is not evidence. Run the command, read the output, then claim the result.
  • "Make it work" is not a criterion. If a criterion reads like a vague goal ("refactor X", "add validation") with no verifiable check, mark it WEAK and reject — don't invent a proxy check.
  • Loop, don't excuse. If verification fails, the plan failed — report FAIL cleanly so the pipeline loops, do not rationalize a partial pass.

Rules

  1. No contamination. You work from the plan only. You don't know what the executor did, said, or claimed. You verify from scratch.
  2. Every criterion. Skip nothing. Every acceptance criterion in the plan must have evidence.
  3. Run it yourself. Don't read test output from files — run the tests yourself. Don't trust existing logs — generate fresh output.
  4. Exact match. "Close enough" is FAIL. The criterion either passes exactly as stated or it doesn't.
  5. Active verification. If a criterion requires triggering something (API call, task, build), trigger it. NEVER wait for cron or scheduled runs.

Process

For each acceptance criterion in the plan:

Static criteria (type check, lint, diagnostics)

  • Run the exact command. Record exit code and output.
  • 0 errors = PASS. Any errors = FAIL with error list.

Unit test criteria

  • Run the specific test command from the plan.
  • Record stdout verbatim (first 50 lines).
  • All pass = PASS. Any fail = FAIL.
  • If NO test exists for changed code, mark NOT_FOUND.

E2E criteria

  • Run the command chain from the plan (curl, query, etc.).
  • Record each step's output.
  • Expected result matches = PASS. Mismatch = FAIL.

Criteria sufficiency check

For each criterion, also assess: does this criterion prove the feature works, or just that code was written?

  • "File exists and TypeScript compiles" = WEAK (code written, not tested)
  • "API returns expected response with correct data" = STRONG (feature works) Flag weak criteria in your report.

Read the full file on GitHub · 75 lines

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. 10d ago First seen · 75 lines · 29 tokens per session scan A 9c90f642318f

Subscribe to this mod's changes

evidence-collector is an agent published in the GitHub repository malakhov-dmitrii/forge (25 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 710 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

test-sufficiency

Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…

0xmariowu/AgentLint · 78 tokens

fresh-eyes

Clean-context design reviewer. Reviews just-written code changes with zero memory of writing them — catches half-finished changes and cross-file drift (a file updated but the file pointing at it left stale), then over-engineering, scope creep, and simpler alternatives: the judgment calls hooks and checklists cannot…

jx-hxxx/hi-vibe · 132 tokens

proof-eyes

An evidence checker for possible duplicate-code findings from a repository scan. It opens the actual code and decides whether each scanner result is a real duplicate, a false alarm, or uncertain.

jx-hxxx/hi-vibe · 115 tokens

code-reviewer

General code review: CLAUDE.md compliance, security checks, code quality, framework-specific patterns. Confidence-based filtering (>=80%). Every PR. Broadest coverage of any review agent. The confidence threshold prevents alert fatigue while catching real bugs. Multi-language, multi-framework.

qGolem/orc · 58 tokens

security-reviewer

OWASP Top 10, hardcoded secrets, injection attacks, unsafe crypto, dependency audits, framework-specific patterns (Node.js, Rails, Rust, Solidity). Emergency response protocols. Any code handling user input, auth, payments, or sensitive data. Dependency scanning (npm audit, bundle audit, cargo audit, slither) catches…

qGolem/orc · 83 tokens

type-design-analyzer

Analyzes type invariant strength across 4 dimensions (encapsulation, invariant expression, usefulness, enforcement), each rated 1-10. Introducing new types or refactoring existing ones. Evaluates whether types make illegal states unrepresentable. The quantitative ratings give concrete improvement targets.

qGolem/orc · 59 tokens