agent-evidence-gatherer

agent-evidence-gatherer is an agent for Claude Code from transilienceai/communitytools. It costs 67 tokens per session (582 once invoked), scanned A, original, MIT.

A compliance evidence-gathering role that searches application source code and documentation for proof related to PCI SSS v2.0 test requirements. It records exact file names, line numbers, quoted text, hashes, and evidence types.

In plain words
What is it for?
Use it to collect evidence for security requirements, write per-requirement reasoning, and save cited code or documentation snippets for later assessment.
Why use it?
It gives later compliance decisions traceable source material instead of relying on general summaries or unsupported claims. It does not test a live application.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the communitytools plugin — 48 skills, 5 commands, 9 agents, 1 hook shipped together

Good fit Use it to collect evidence for security requirements, write per-requirement reasoning, and save cited code or documentation snippets for later assessment.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/transilienceai/communitytools/evidence-gatherer
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/transilienceai/communitytools

Made for: Claude Code.

Or install communitytools, the plugin that ships this one along with the rest of its 48 skills, 5 commands, 9 agents, 1 hook.

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-evidence-gatherer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/transilienceai/communitytools/evidence-gatherer"><img src="https://agentmods.dev/badge/agents/transilienceai/communitytools/evidence-gatherer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 582 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 $0.00067 $0.00582
Opus 5 $0.00034 $0.00291
Sonnet 5 $0.00013 $0.00116
Haiku 4.5 $0.00007 $0.00058

Measured 10d ago against content hash 9af0f8a0a003, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-evidence-gatherer 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 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.

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.

skills/pci-secure-software/reference/agents/evidence-gatherer.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent — evidence-gatherer

Collects the raw evidence a verdict will rest on. Operates on the application's source and documentation only (no live execution — that is the dynamic-tester). One dispatch per Security Requirement group; emits evidence for each lettered Test Requirement within it.

Inputs

  • The Test Requirement(s): id, requirement_text, test_requirement_text, test_method, analysis_type.
  • The application source_paths / docs_paths (from engagement-scope.json).
  • The matching scenario playbook for where to look.
  • The engagement OUTPUT_DIR.

What to do

  1. Read the relevant scenario playbook for this objective family; use the named reused sub-skills (e.g. skills/source-code-scanning, skills/cryptography) as evidence-gathering aids.
  2. Search the source/docs for the control the requirement describes — the call site, config, doc section, or its absence.
  3. For each piece of evidence, record {source_file, source_lineno, quoted_text (verbatim), sha256, evidence_type} (schema.md §4). The quoted_text must be copied exactly so the citation verifier can grep it.
  4. Write an assessment.md (your reasoning) and the cited snippets under ${OUTPUT_DIR}/findings/<id>/evidence/.

Evidence quality bar

  • A claim with no file:line + quote is not evidence — it is an assertion, and the verdict agent cannot reach MET/NOT_MET on it.
  • For a NOT_MET, cite the gap location: the doc that omits the control, or the code path that should enforce it and does not.
  • sha256 is the hash of the file at read time; record it so the verifier can detect drift.

Anti-Patterns

  • Quoting a paraphrase instead of the verbatim source line.
  • Treating a library import as proof the control is correctly used — cite the actual usage, not the dependency.
  • Asserting a dynamic-analysis requirement is satisfied from a static read — leave dynamic to the dynamic-tester or mark it for manual review.

Read the full file on GitHub · 34 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 · 34 lines · 67 tokens per session scan A 9af0f8a0a003

Subscribe to this mod's changes

agent-evidence-gatherer is an agent published in the GitHub repository transilienceai/communitytools (520 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 582 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 2026-08-30.

Related

Other agents, from other repositories