claim_ref_alignment_audit_agent

claim_ref_alignment_audit_agent is an agent for Claude Code from Lzy599775/agent-auto-sci-skills. It costs 44 tokens per session (10,425 once invoked), scanned A, a copy of claim_ref_alignment_audit_agent, MIT.

A citation-audit agent that checks whether claims in a draft are supported by the text of their cited sources and flags unsupported or uncited statements.

In plain words
What is it for?
Use it to audit claims in an academic draft and pass evidence-based findings to the paper-formatting stage.
Why use it?
It helps catch inaccurate citations, overstated claims, and violations of writing constraints before formatting or submission.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions Codex.

Good fit Use it to audit claims in an academic draft and pass evidence-based findings to the paper-formatting stage.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/lzy599775/agent-auto-sci-skills/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/Lzy599775/agent-auto-sci-skills

Made for: Claude Code.

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/lzy599775/agent-auto-sci-skills/claim_ref_alignment_audit_agent/github.svg)](https://agentmods.dev/agents/lzy599775/agent-auto-sci-skills/claim_ref_alignment_audit_agent)
Your own site
<a href="https://agentmods.dev/agents/lzy599775/agent-auto-sci-skills/claim_ref_alignment_audit_agent"><img src="https://agentmods.dev/badge/agents/lzy599775/agent-auto-sci-skills/claim_ref_alignment_audit_agent/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.

agentmods 80×15 button for claim_ref_alignment_audit_agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/lzy599775/agent-auto-sci-skills/claim_ref_alignment_audit_agent"><img src="https://agentmods.dev/badge/agents/lzy599775/agent-auto-sci-skills/claim_ref_alignment_audit_agent.svg" alt="Reviewed on agentmods" width="80" 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 10,425 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 94% copy Near-identical to another mod 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 $0.10425
Opus 5 $0.00022 $0.05213
Sonnet 5 $0.00009 $0.02085
Haiku 4.5 $0.00004 $0.01043

Measured 5d ago against content hash 22a8ef1e26b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 5d 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.

Origin

This is a copy

94% identical to claim_ref_alignment_audit_agent — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/urban-exposure-review-radar-workflow/subskills/academic-research-suite/ars/academic-pipeline/agents/claim_ref_alignment_audit_agent.md · 383 lines

How it starts

The opening of the file, as written. The whole thing — 383 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.

Experiment-backed claims are NOT yours to judge (#260). A claim whose manifest entry carries planned_experiment_ids[] is backed by the scholar's own experiment provenance, not by a retrieved reference. Its faithfulness verdict (experiment_alignment_results[] with verdict ∈ {ALIGNED, OVERSTATED, NOT_SUPPORTED_BY_PROVENANCE, PROVENANCE_INSUFFICIENT}) is computed by the integrity_verification_agent at the Stage 2.5/4.5 gate (mirroring the #261 figure-fidelity pattern), NOT here. You must (a) NOT emit any experiment_alignment_results[] row, and (b) NOT misroute an experiment-only sentence into claim_audit_results[] or uncited_assertions[] just because it has no <!--ref:slug--> marker — see the D4-c carve-out below and the Manifest cross-reference precedence rule. A mixed-evidence claim (manifest entry carries BOTH planned_refs AND planned_experiment_ids) DOES get your normal citation-path treatment for its cited portion (a claim_audit_results[] row); the experiment path is the integrity agent's separate row, and the gate combines them worst-verdict-wins. Mixed-evidence is the ONE case where the same claim legitimately appears on both sides.

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).

Read the full file on GitHub · 383 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. 5d ago First seen · 383 lines · 44 tokens per session scan A 22a8ef1e26b9

Subscribe to this mod's changes

claim_ref_alignment_audit_agent is an agent published in the GitHub repository Lzy599775/agent-auto-sci-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 10,425 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to claim_ref_alignment_audit_agent, differing in 4 lines, and is treated as a copy.