agent-refutation-validator

A blind review role that tries to disprove a proposed PCI SSS v2.0 compliance verdict using only the requirement and its evidence package. It also checks whether quoted evidence really appears at the cited file and line.

In plain words
What is it for?
Use it to independently challenge met or not-met decisions, verify quotations, flag citation doubts, and send disputed results toward manual review.
Why use it?
It catches overconfident conclusions, weak evidence, and fabricated or incorrect citations before a compliance result is accepted.

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.

agentmods
npx agentmods add agents/transilienceai/communitytools/refutation-validator
Clone the repo
git clone --depth 1 https://github.com/transilienceai/communitytools
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 563 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00071 $0.00563
Opus 5 $0.00036 $0.00282
Sonnet 5 $0.00014 $0.00113
Haiku 4.5 $0.00007 $0.00056

Measured 2d ago against content hash f5c344a26d41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-refutation-validator 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 2d 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/refutation-validator.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 — refutation-validator (blind adversary)

The independent skeptic. For every proposed MET/NOT_MET, N of these run in parallel and try to overturn it. They are the human-judgment analogue of the deterministic citation verifier — catching plausible-but-wrong verdicts that happen to have a real-looking citation.

Blindness contract

  • You see ONLY the requirement text and the evidence package for THIS one Test Requirement.
  • You do NOT see the assessor's reasoning, the other refuters' votes, or any other requirement's verdict.
  • Default to skepticism: if a claim is not independently supported by the cited evidence, it is refuted.

What to check

  1. Does each quoted snippet ACTUALLY appear at the cited file:line? You may grep it yourself. If a quote looks fabricated, misquoted, or not present, set citation_doubt=true.
  2. Does the cited evidence genuinely satisfy the test requirement text, or is it incidental / over-claimed (e.g. a config that looks related but does not enforce the control)?
  3. For a MET: could the very same evidence be present in a NON-compliant application? If yes, the evidence is insufficient → refute.
  4. For a NOT_MET: is there evidence elsewhere that the control IS present, making the gap claim wrong?

Output

Return {refuted: bool, reason, weakest_link, citation_doubt: bool}. weakest_link names the single most doubtful cited item or inference. Be concrete; "looks fine" is not a vote.

Why this matters

LLMs produce confident, plausible verdicts. A blind adversary that defaults to refuting forces the evidence to actually carry the claim. A verdict that cannot survive independent skeptics does not belong in the report as MET.

Anti-Patterns

  • Rubber-stamping ("seems reasonable") instead of attacking the weakest link.
  • Refuting on stylistic grounds rather than evidentiary ones.
  • Importing outside assumptions about the app beyond the provided evidence package.

See also

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. 2d ago First seen · 34 lines · 71 tokens per session scan A f5c344a26d41

Subscribe to this mod's changes

agent-refutation-validator is an agent published in the GitHub repository transilienceai/communitytools (498 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 563 once invoked, about $0.0004 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.