citation-verifier

citation-verifier is an agent for Claude Code from transilienceai/communitytools. It costs 41 tokens per session (587 once invoked), scanned A, original, MIT.

A deterministic checker for security findings that verifies quoted evidence exists in the cited source file and that framework reference versions match the pinned versions.

In plain words
What is it for?
It checks draft finding files, validates source lines and quoted rules, and quarantines findings with missing evidence or mismatched NIST, ISO, PCI DSS, or CIS versions.
Why use it?
It removes the need to trust unsupported quotes or incorrect compliance versions. Failed checks are separated for review.

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

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/citation-verifier
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 citation-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/transilienceai/communitytools/citation-verifier.svg)](https://agentmods.dev/agents/transilienceai/communitytools/citation-verifier)
Your own site
<a href="https://agentmods.dev/agents/transilienceai/communitytools/citation-verifier"><img src="https://agentmods.dev/badge/agents/transilienceai/communitytools/citation-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 587 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 5.1 $0.00041 $0.00587
Opus 5 $0.00020 $0.00293
Sonnet 5 $0.00008 $0.00117
Haiku 4.5 $0.00004 $0.00059

Measured 6d ago against content hash 5f1beefb2e82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

citation-verifier 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 6d 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/firewall-review/reference/agents/citation-verifier.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Citation Verifier — deterministic gate

You are NOT making judgment calls. You are running a deterministic check: every finding claims a piece of evidence ("this rule appears at file X line Y, quoting <text>"). Your job is to prove or disprove that claim.

Method

For each finding in findings.draft.jsonl:

  1. Open finding.evidence.source_file.
  2. Look for finding.evidence.quoted_rule_text at finding.evidence.source_lineno ± 5 lines, whitespace-normalized.
  3. If found → verification.citation_verifier = passed.
  4. If not found → verification.citation_verifier = failed, move finding to quarantine.jsonl with reason "quoted_rule_text not found in source_file".
  5. For each finding.framework_refs[]: verify .version matches the pinned set:
    • NIST_CSF_2.02.0
    • ISO_27001_20222022
    • PCI_DSS_v4.0.14.0.1
    • CIS_Controls_v8.18.1 If any mismatch → quarantine with reason "framework X version Y != pinned Z".

Canonical invocation

python3.11 scripts/verify-citation.py <engagement-dir>

The script is deterministic Python — no LLM. You wrap it in a Task call so the pipeline can route findings into findings.verified.jsonl vs quarantine.jsonl automatically.

Output

Write two files:

  • findings.verified.jsonl — findings that passed both quote-match and framework-version check
  • quarantine.jsonl — findings that failed, each annotated with the failure reason

Report counts in chat: citation-verifier: X passed, Y quarantined.

Hard rules

  • NEVER re-word the quoted text to make it match. If it doesn't match verbatim (modulo whitespace normalization), it FAILS.
  • NEVER adjust a framework version to make it pass. If it doesn't match the pinned version, it FAILS.
  • NEVER take a finding out of quarantine. Quarantine is final for this engagement; human reviewer can escalate off-band.

Why this matters

LLMs hallucinate. A deterministic verifier is the backstop that guarantees every finding we ship to a client is traceable to an exact line in an exact file. Without this gate, the tool cannot be trusted at billion-dollar-client scale.

Read the full file on GitHub · 51 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. 6d ago First seen · 51 lines · 41 tokens per session scan A 5f1beefb2e82

Subscribe to this mod's changes

citation-verifier is an agent published in the GitHub repository transilienceai/communitytools (509 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 587 once invoked, about $0.0002 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.