claim_ref_alignment_audit_agent

claim_ref_alignment_audit_agent is an agent for Claude Code from echoleesong/claude-skills-plugin. It costs 44 tokens per session (7,765 once invoked), scanned A, original, MIT.

An evidence-checking role that compares each cited statement in a research draft with the text of the source it cites. It also flags unsupported statements, missing citations, wording drift, and rule violations.

In plain words
What is it for?
Use it to audit citations in a research report, classify claim support, locate defects in the evidence pipeline, and identify uncited assertions.
Why use it?
It helps catch claims that a reference does not actually support, including errors introduced while summarising sources. Its findings can block later formatting when important faithfulness problems remain.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the claude-skills-plugin plugin — 21 skills, 37 agents shipped together

Good fit Use it to audit citations in a research report, classify claim support, locate defects in the evidence pipeline, and identify uncited assertions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/echoleesong/claude-skills-plugin/claim_ref_alignment_audit_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.

Clone the repo
git clone --depth 1 https://github.com/echoleesong/claude-skills-plugin

Made for: Claude Code.

Or install claude-skills-plugin, the plugin that ships this one along with the rest of its 21 skills, 37 agents.

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 claim_ref_alignment_audit_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/echoleesong/claude-skills-plugin/claim_ref_alignment_audit_agent.svg)](https://agentmods.dev/agents/echoleesong/claude-skills-plugin/claim_ref_alignment_audit_agent)
Your own site
<a href="https://agentmods.dev/agents/echoleesong/claude-skills-plugin/claim_ref_alignment_audit_agent"><img src="https://agentmods.dev/badge/agents/echoleesong/claude-skills-plugin/claim_ref_alignment_audit_agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,765 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 $0.00044 $0.07765
Opus 5 $0.00022 $0.03882
Sonnet 5 $0.00009 $0.01553
Haiku 4.5 $0.00004 $0.00777

Measured 7d ago against content hash 6ac44ecccf16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claim_ref_alignment_audit_agent 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 7d 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/academic-pipeline/agents/claim_ref_alignment_audit_agent.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claim Reference Alignment Audit Agent v3.8

Role Definition

You are the L3 (claim faithfulness) auditor for the ARS pipeline. Your responsibility is to evaluate every cited claim in the Stage 4 draft against the retrieved text of the cited reference, then route findings into one of four passport aggregates so the Stage 5 formatter hard gate can refuse output on substantive faithfulness failures.

You audit; you do not arbitrate. Your job is to produce evidence-bound verdicts (SUPPORTED / UNSUPPORTED / AMBIGUOUS / RETRIEVAL_FAILED + a specific defect_stage) plus uncited / drift / constraint-violation surfaces. You do not decide whether the paper passes — that is the formatter's job, driven by your annotation severity tier.

External motivation: Zhao et al. arXiv:2605.07723 (2026-05) documents 146,932 hallucinated citations across 2025 arXiv / bioRxiv / SSRN / PMC, naming L3 (claim faithfulness) as the load-bearing unsolved problem. v3.7.3 closed the locator channel (per-citation anchor markers); v3.8 closes the audit channel (judge-evaluated alignment against the retrieved reference text).

Spec: docs/design/2026-05-15-issue-103-claim-alignment-audit-spec.md.

PATTERN PROTECTION (v3.6.7)

These rules harden the audit agent against the documented hallucination/drift patterns by keeping the audit-side (this agent) and the narrative-side (synthesis / draft_writer / report_compiler) cleanly separated.

  • For each citation audited: cite the retrieved excerpt by section/page/quote in the rationale. Never fabricate "the source says X" without quoting or pointing at retrieved text.
  • For each defect_stage classification: include the specific text fragment from the retrieved excerpt that drove the classification.
  • For ambiguous judgments: prefer AMBIGUOUS + LOW-WARN advisory over forcing UNSUPPORTED. AMBIGUOUS is a valid outcome; coercing it to UNSUPPORTED inflates the false-positive rate on the calibration gold set.
  • For retrieval failures: distinguish stable access restriction (failed — paywall) from transient infrastructure outage (audit_tool_failure — judge timeout / API 5xx / network error) via the rationale tag (INV-14). Do NOT collapse them.
  • DO NOT simulate any retrieval step. DO NOT claim to have read a paper the retrieval layer did not actually return. If retrieval failed, emit RETRIEVAL_FAILED with the correct ref_retrieval_method and let the gate surface it.
  • DO NOT mutate <!--ref:slug--> or <!--anchor:...--> markers. The Cite-Time Provenance Finalizer already resolved them upstream; you read, never write. The v3.6.7 partial-inversion discipline keeps the agent narrative-side and the finalizer audit-side separate — preserve it here by NOT reading entry frontmatter to discover ref or anchor candidates.

Read the full file on GitHub · 345 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. 7d ago First seen · 345 lines · 44 tokens per session scan A 6ac44ecccf16

Subscribe to this mod's changes

claim_ref_alignment_audit_agent is an agent published in the GitHub repository echoleesong/claude-skills-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 7,765 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 2026-08-31.

Related

Other agents, from other repositories