audit-reproducibility

audit-reproducibility is a skill for Claude Code from pedrohcgs/Claude-Mini. It costs 54 tokens per session (2,209 once invoked), scanned A, original, MIT.

A check that compares numbers stated in a research paper with the results produced by its R, Stata, or Python analysis code.

In plain words
What is it for?
Use it before submitting a paper, releasing code for replication, making a major revision, or committing manuscript and analysis changes.
Why use it?
It catches cases where the analysis changed but the manuscript, tables, or replication package still contain old or inaccurate numbers.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; positional $N argument.

Good fit Use it before submitting a paper, releasing code for replication, making a major revision, or committing manuscript and analysis changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pedrohcgs/claude-mini/audit-reproducibility
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 pedrohcgs/Claude-Mini --skill audit-reproducibility
Clone the repo
git clone --depth 1 https://github.com/pedrohcgs/Claude-Mini

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-reproducibility

README.md
[![agentmods](https://agentmods.dev/badge/skills/pedrohcgs/claude-mini/audit-reproducibility/github.svg)](https://agentmods.dev/skills/pedrohcgs/claude-mini/audit-reproducibility)
Your own site
<a href="https://agentmods.dev/skills/pedrohcgs/claude-mini/audit-reproducibility"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-mini/audit-reproducibility/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-reproducibility

Your own site · 80×15
<a href="https://agentmods.dev/skills/pedrohcgs/claude-mini/audit-reproducibility"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-mini/audit-reproducibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,209 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 $0.00054 $0.02209
Opus 5 $0.00027 $0.01104
Sonnet 5 $0.00011 $0.00442
Haiku 4.5 $0.00005 $0.00221

Measured 10d ago against content hash a90b0767e57b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

audit-reproducibility 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 10d 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-reproducibility/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Reproducibility

Compare numeric claims in a manuscript (point estimates, standard errors, p-values, counts) against the actual outputs produced by the analysis pipeline. Report PASS / FAIL per claim against the tolerance thresholds defined in .claude/rules/replication-protocol.md.

Core principle: If the paper says ATT = -1.632 (0.584) and the code produces -1.628 (0.591), we verify — numerically — that the difference is within the documented tolerance. No more "looks close enough" eyeballing.

When to use

  • Before submission. Catches the "I updated the analysis but forgot to update Table 2" bug.
  • Before releasing a replication package. Verifies the code actually reproduces the paper.
  • After a major revision. Ensures the paper still matches the latest code.
  • Quality-gate in /commit. Pair with a pre-commit invocation on manuscript + analysis changes.

Inputs

  • $0 — path to the manuscript (.tex, .qmd, .md, .pdf). Required.
  • $1 — path to the outputs directory. Defaults to scripts/R/_outputs/. Can be _targets/objects/, a Stata .do-file log directory, etc.

Workflow

Phase 0: Pre-flight

  1. Read replication-protocol.md for the tolerance thresholds currently in effect.
  2. Verify the outputs directory exists and is non-empty. If empty or stale (older than the manuscript), prompt the user to re-run their pipeline (e.g., Rscript scripts/R/00_run_all.R) before auditing.
  3. Ensure a sessionInfo.txt or equivalent environment capture exists in the outputs dir.

Phase 1: Extract claims from the manuscript

Parse the manuscript for numeric claims. Patterns to match:

  • Point-estimate + SE: ATT = -1.632 (0.584), $\beta = 0.342$ (0.091), hat{\tau} = 1.28** with starred significance
  • Table cells: & -1.632$^{***}$ & 0.584 & in LaTeX table environments
  • Counts: our sample of 2,847 firms, $N = 2{,}847$
  • Summary stats: mean = 0.423, SD = 0.087
  • P-values: p < 0.01, $p = 0.003$

Read the full file on GitHub · 171 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. 10d ago First seen · 171 lines · 54 tokens per session scan A a90b0767e57b

Subscribe to this mod's changes

audit-reproducibility is a skill published in the GitHub repository pedrohcgs/Claude-Mini (11 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 2,209 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.