audit-attribution

audit-attribution is a skill for Claude Code from chrisgagne/grounded-forge. It costs 60 tokens per session (3,637 once invoked), scanned A, original, MIT.

A review of an essay or draft that looks for under-attribution: presenting a distinctive structure or synthesis as original even when it closely follows earlier work. It is not a general fact check.

In plain words
What is it for?
It helps find the closest related works, classify the overlap, and suggest specific provenance or attribution changes.
Why use it?
It makes the boundary between borrowed foundations and the author’s own contribution visible to readers.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the grounded-forge plugin — 12 skills, 2 agents, 1 hook shipped together

Good fit It helps find the closest related works, classify the overlap, and suggest specific provenance or attribution changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chrisgagne/grounded-forge/audit-attribution
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 chrisgagne/grounded-forge --skill audit-attribution
Clone the repo
git clone --depth 1 https://github.com/chrisgagne/grounded-forge

Made for: Claude Code.

Or install grounded-forge, the plugin that ships this one along with the rest of its 12 skills, 2 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 audit-attribution

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/audit-attribution.svg)](https://agentmods.dev/skills/chrisgagne/grounded-forge/audit-attribution)
Your own site
<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/audit-attribution"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/audit-attribution.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,637 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 $0.00060 $0.03637
Opus 5 $0.00030 $0.01818
Sonnet 5 $0.00012 $0.00727
Haiku 4.5 $0.00006 $0.00364

Measured 8d ago against content hash 3dd79b75f789, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

audit-attribution 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-attribution/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit attribution

Run an essay or draft through the library to surface under-attribution: the gap between an essay properly citing sources and an essay where a careful reader can tell what's being built on versus what's being contributed. Citation count is not the metric; the metric is whether the build/contribute boundary is visible from the text alone.

Why this skill exists

When synthesising across multiple bodies of work, an author can produce an essay that:

  1. Properly cites individual sources, and
  2. Reproduces the structure, catalogue, or argumentative shape of one source closely enough that a reader of that source recognises it as the same territory, but
  3. Frames the synthesis as the author's own without naming the closest neighbours in the lineage.

This is not plagiarism—citations exist—but it is under-attribution: the reader can't tell from the text alone what the author is building on versus contributing. The fix is provenance markers that make the build/contribute boundary visible.

A 30-citation essay can still under-attribute. Citation breadth is not citation depth.

When to use

  • Sanity-checking a draft before publication (blog post, paper, book chapter, board paper).
  • After heavy revision where multiple sources have been integrated and the author's distinctive contribution may have been buried among attributions.
  • When the audience includes readers familiar with one or more of the source bodies of work: they're the readers most likely to feel the under-attribution.

When not to use

  • Light editorial polish: this skill is heavyweight, designed for substantive synthesis work.
  • Fact-checking individual claims against the corpus: that's answer-from-corpus with an audit framing, not this skill.
  • First-draft generation: this is a late-stage check, not a generation tool.

Procedure

Step 1: Read the essay and identify load-bearing contributions

Read the essay in full. Identify:

  • The 1-3 distinctive claims the author is contributing. The synthesis is usually one or two specific claims, not the whole essay. Surface these explicitly before any neighbour scan: buried distinctive claims are a separate failure mode (silent demotion) that the audit must flag.
  • The named coinages in the essay: capitalised phrases, in-quotes terms, idiosyncratic vocabulary that may be someone else's. Examples: "Poetic Attunement", "Inherent Simplicity", "Self-Improvement Trap", "Lethal Paradigm", "Build/Contribute Boundary".
  • The argument's shape: section logic, what it catalogues, what it prescribes, the diagnosis-prescription arc.

Read the full file on GitHub · 226 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 · 226 lines · 0 tokens per session scan A 3dd79b75f789

Subscribe to this mod's changes

audit-attribution is a skill published in the GitHub repository chrisgagne/grounded-forge (7 stars, last pushed 17d ago), licensed MIT. It adds 60 tokens to every session and 3,637 once invoked, about $0.0003 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.