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.
git clone --depth 1 https://github.com/transilienceai/communitytoolsWrote 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.
[](https://agentmods.dev/agents/transilienceai/communitytools/evidence-gatherer)<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.
<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>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 | $0.00067 | $0.00582 |
| Opus 5 | $0.00034 | $0.00291 |
| Sonnet 5 | $0.00013 | $0.00116 |
| Haiku 4.5 | $0.00007 | $0.00058 |
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.
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(fromengagement-scope.json). - The matching scenario playbook for where to look.
- The engagement
OUTPUT_DIR.
What to do
- 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. - Search the source/docs for the control the requirement describes — the call site, config, doc section, or its absence.
- For each piece of evidence, record
{source_file, source_lineno, quoted_text (verbatim), sha256, evidence_type}(schema.md §4). Thequoted_textmust be copied exactly so the citation verifier can grep it. - 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.
sha256is 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.
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.
- 10d ago First seen · 34 lines · 67 tokens per session scan A 9af0f8a0a003
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.
Other agents, from other repositories
auth-tester
Test authorization and access control across endpoints with ≥2 auth states. Returns IDOR / BFLA / auth-bypass findings.
command-expert
Create CLI commands for automation and tooling. Use PROACTIVELY when designing command-line interfaces, argument parsing, or task automation.
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
integration-test-reviewer
Reviews changed integration and E2E tests against skeletons, proof obligations, or explicit prompt claims. Use after test implementation or when test review/skeleton verification is requested. Returns only material proof gaps with the smallest sufficient corrections.
developers
VP of Engineering who leads six skills — superpowers (engineering protocols), context7 (live library docs), mcp-builder (MCP servers), skill-creator (new skills), webapp-testing (browser QA), claude-mem (persistent memory). Use PROACTIVELY for any coding, debugging, testing, docs-lookup, MCP-server, skill-authoring or…
js-analyst
Deep JavaScript analysis — secrets, DOM sinks, hidden API endpoints. Returns enriched JS intel for the orchestrator.