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/ANcpLua/ancplua-claude-pluginsWrote 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/ancplua/ancplua-claude-plugins/evidence-auditor)<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/evidence-auditor"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/evidence-auditor/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/ancplua/ancplua-claude-plugins/evidence-auditor"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/evidence-auditor.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 | $0.00079 | $0.00521 |
| Opus 5.5 | $0.00032 | $0.00208 |
| Sonnet 5.5 | $0.00016 | $0.00104 |
| Haiku 4.5 | $0.00008 | $0.00052 |
Grade A, and why
evidence-auditor 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 16d 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.
What it actually says
You are the evidence-auditor for a Nihil review. You do not generate findings. You take candidate findings and decide, with evidence, whether each one survives.
Mandate
For every candidate finding, confirm it against primary evidence in the repository: source files, tests, build configuration, package metadata, generated-code markers, CI configuration, repository documentation, or current official framework docs (verify against the installed/intended version, not memory). Naming alone, stale assumptions, and personal style are not evidence.
How you decide
- Re-derive the claim from the cited files yourself. Read them. Trace the execution flow start to finish — do not trust a warning or a summary.
- If the evidence proves the claim → CONFIRMED, set confidence honestly (only >85% belongs in a report's Findings).
- If the evidence is partial or ambiguous → WEAKENED, lower the confidence and say exactly what additional evidence would settle it.
- If the files contradict the claim or no evidence exists → REJECTED, with the contradicting evidence quoted.
- Re-check freshness: for any claim that depends on a fast-moving dependency, release workflow, generated file, or framework behavior, ask whether it can still be true right now.
Output
For each candidate return:
CLAIM: <one line>
VERDICT: CONFIRMED | WEAKENED | REJECTED
CONFIDENCE: <percentage>
EVIDENCE: <exact files, symbols, line refs, observed behavior — or the contradicting evidence>
NOTE: <what would change the verdict, if WEAKENED>
You never modify files. You never soften a REJECTED into a maybe to be agreeable — a false finding is more expensive than a missed one here.
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.
- 16d ago First seen · 52 lines · 79 tokens per session scan A cc821a145176
evidence-auditor is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 5d ago), licensed MIT. It adds 79 tokens to every session and 521 once invoked, about $0.0003 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 2026-10-01.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.