audit-references

audit-references is a skill for Claude Code, Codex from petar-djukic/writing-skills. It costs 117 tokens per session (1,489 once invoked), scanned A, original, MIT.

A citation-checking tool for papers and documents that verifies whether cited sources support the claims made in the text.

In plain words
What is it for?
Use it to check Pandoc citations against a references file and compare claims with the cited papers from sources such as arXiv or Google Scholar.
Why use it?
It helps find citations that are missing, unsupported, misattributed, or unavailable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to check Pandoc citations against a references file and compare claims with the cited papers from sources such as arXiv or Google Scholar.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/petar-djukic/writing-skills/audit-references
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.

Any agent
npx skills add petar-djukic/writing-skills --skill audit-references
Clone the repo
git clone --depth 1 https://github.com/petar-djukic/writing-skills

Made for: Claude Code, Codex.

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 audit-references

README.md
[![agentmods](https://agentmods.dev/badge/skills/petar-djukic/writing-skills/audit-references/github.svg)](https://agentmods.dev/skills/petar-djukic/writing-skills/audit-references)
Your own site
<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/audit-references"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/audit-references/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 audit-references

Your own site · 80×15
<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/audit-references"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/audit-references.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,489 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 $0.00117 $0.01489
Opus 5 $0.00059 $0.00745
Sonnet 5 $0.00023 $0.00298
Haiku 4.5 $0.00012 $0.00149

Measured 11d ago against content hash 4206298326a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

audit-references 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 11d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/extract_citations.py, scripts/testdata/test_extract_citations.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/audit-references/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit references (citation verification)

This skill verifies that the citations in a document actually say what the author claims they say. It complements update-references (which discovers new papers) by auditing existing citations for correctness.

The output is an audit report: one entry per citation, with a verdict (supported, unsupported, misattributed, not-found) and the evidence from the source paper.

Where things live

  • Document: The markdown file the user points you at, or the most obvious draft in the working directory. Look for .md files that contain [@ citations.
  • Database: references.yaml in the working directory (or at the nearest ancestor that has one). This is the Citation Style Language (CSL) YAML bibliography that pandoc and update-references both use.
  • PDFs/papers: <db-dir>/pdfs/ and <db-dir>/papers/ — the same locations update-references uses. If a paper was already fetched, reuse its markdown.
  • Audit report: <db-dir>/audits/<document-stem>-audit.md, using the template in <skill>/references/audit-template.md.

Prerequisites

The document must use pandoc citation syntax: [@citation-id], [@id1; @id2], or @citation-id inline. The citation ids must match entries in references.yaml.

If references.yaml does not exist in the paper directory, stop and tell the user. They need to create it first (using update-references or manually).

Running the scripts

This skill and the update-references scripts it calls run in the pixi-managed environment that ships beside the skills. The agent provisions it on repo open via <agent-dir>/scripts/ensure-env.sh; the commands below use $RUN:

RUN="pixi run --manifest-path <skill>/../../pixi.toml python"

No pip install is needed — the environment supplies PyYAML and the PDF libraries.

The workflow

1. Extract citations

Run the extraction script to get every citation and its surrounding context:

$RUN <skill>/scripts/extract_citations.py <document-path>

Read the full file on GitHub · 159 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 159 lines · 117 tokens per session scan A 4206298326a7

Subscribe to this mod's changes

audit-references is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 7d ago), licensed MIT. It adds 117 tokens to every session and 1,489 once invoked, about $0.0006 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 skills, from other repositories

humanizer

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…

NulightJens/humanizer-stack · 111 tokens

structural-humanizer

Remove the discourse-level (structural) signs of AI writing that survive surface editing: stated lessons and moral-of-the-story closers, tidy single-track arcs, embodied-emotion performance ("chest tightened"), vague allusions instead of named references, unbroken linear structure, and shape convergence across pieces.…

NulightJens/humanizer-stack · 188 tokens

story-import

A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.

zenstory-ai/oh-story-claudecode · 98 tokens

story-review

A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.

zenstory-ai/oh-story-claudecode · 74 tokens

story-long-analyze

A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.

zenstory-ai/oh-story-claudecode · 173 tokens

story-deslop

A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.

zenstory-ai/oh-story-claudecode · 62 tokens