openakari: Skill for Claude Code

.claude/skills/audit-references/SKILL.md

audit-references is a skill for Claude Code from victoriacity/openakari. It costs 22 tokens per session (1,562 once invoked), scanned A, original, MIT.

A reference-checking skill for projects or publication drafts that contain literature notes or citations. It fetches each cited URL and checks that it matches the claimed paper.

In plain words
What is it for?
Use it after a literature review, before publishing a document with citations, or when checking whether a reference may be fabricated.
Why use it?
It catches incorrect, missing, or mismatched references before research notes or published material are shared.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is victoriacity/openakari's own configuration. It tells Claude Code how to work on openakari itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything openakari configures →

Reuse

Borrowing it

Nothing to install: this file belongs to victoriacity/openakari. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/victoriacity/openakari/main/.claude/skills/audit-references/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/victoriacity/openakari

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 audit-references

README.md
[![agentmods](https://agentmods.dev/badge/skills/victoriacity/openakari/audit-references.svg)](https://agentmods.dev/skills/victoriacity/openakari/audit-references)
Your own site
<a href="https://agentmods.dev/skills/victoriacity/openakari/audit-references"><img src="https://agentmods.dev/badge/skills/victoriacity/openakari/audit-references.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,562 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 $0.00022 $0.01562
Opus 5 $0.00011 $0.00781
Sonnet 5 $0.00004 $0.00312
Haiku 4.5 $0.00002 $0.00156

Measured 8d ago against content hash 04771820e866, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 8d 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.

.claude/skills/audit-references/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit-references

Verify every literature note and cited reference in a project or publication draft by fetching each URL and confirming the paper's identity. This is a mechanical verification procedure — do not rely on memory or judgment about whether a paper is real.

When to use this

  • Pre-publication gate: Before committing or sharing any publication draft, run this to verify all cited references.
  • Post-literature-review: After /lit-review produces notes, run this to verify them.
  • Periodic audit: On any project with a literature/ directory that hasn't been audited recently.
  • Incident response: When a hallucination is suspected in any literature note.

Step 1: Discover literature notes

If the argument is a project directory (e.g., projects/sample-project/):

  • Glob for <project>/literature/*.md (exclude synthesis.md or any non-note files)
  • These are the notes to audit

If the argument is a publication draft file:

  • Read the draft and extract all citation references (author-year style, footnotes, or bibliography entries)
  • For each citation, find the corresponding literature note in the project's literature/ directory
  • Flag any citations that have no corresponding literature note

Step 2: Extract claims from each note

For each literature note, extract:

  1. Claimed title — from the Citation: line or # <title> heading
  2. Claimed authors — from the Citation: line
  3. Claimed URL/DOI — from the URL/DOI: line
  4. Claimed venue/year — from the Citation: line
  5. Current verified field — if present in the note

Step 3: Fetch and verify each URL

For each URL/DOI:

  1. Fetch the URL using WebFetch. For arxiv URLs, fetch the abstract page (e.g., https://arxiv.org/abs/XXXX.XXXXX).
  2. Extract the actual title from the fetched page.
  3. Extract actual authors from the fetched page.
  4. Compare title: Does the fetched title match the claimed title? Use fuzzy matching — minor differences in capitalization, punctuation, or subtitle formatting are acceptable. A completely different topic is a FAIL.
  5. Compare authors: Does at least one claimed author appear in the fetched author list? One match is sufficient.
  6. Record the result: PASS (title matches, author matches), FAIL (title or author mismatch), or ERROR (URL unreachable, 404, paywall, etc.).

Read the full file on GitHub · 133 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. 8d ago First seen · 133 lines · 22 tokens per session scan A 04771820e866

Subscribe to this mod's changes

audit-references is a skill published in the GitHub repository victoriacity/openakari (47 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 1,562 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens