differential-audit

differential-audit is a skill for Claude Code from pedrohcgs/claude-code-my-workflow. It costs 115 tokens per session (1,266 once invoked), scanned A, original, MIT.

A method for comparing two implementations of the same computation, such as a rewrite, port, refactor, or new version. It defines what agreement can prove, freezes inputs and expected outputs, and checks every result channel.

In plain words
What is it for?
Use it to audit parity between implementations, fix comparison inputs and thresholds, test the comparator, and document what agreement means.
Why use it?
It prevents matching outputs from being mistaken for proof of correctness and makes disagreements easier to investigate.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to audit parity between implementations, fix comparison inputs and thresholds, test the comparator, and document what agreement means.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pedrohcgs/claude-code-my-workflow/differential-audit
About the project

claude-code-my-workflow is a forkable setup for using Claude Code to produce and review academic papers, slides, data analyses, and replication packages. Researchers use its agents, skills, rules, hooks, and quality checks to coordinate these tasks and verify their results. The catalogue entries define the reusable workflow components for Claude Code.

pedrohcgs/claude-code-my-workflow · 1,567 stars · on GitHub · psantanna.com

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-code-my-workflow --skill differential-audit
Clone the repo
git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow

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 differential-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/differential-audit.svg)](https://agentmods.dev/skills/pedrohcgs/claude-code-my-workflow/differential-audit)
Your own site
<a href="https://agentmods.dev/skills/pedrohcgs/claude-code-my-workflow/differential-audit"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/differential-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,266 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00115 $0.01266
Opus 5 $0.00057 $0.00633
Sonnet 5 $0.00023 $0.00253
Haiku 4.5 $0.00012 $0.00127

Measured 8d ago against content hash 72335e59883f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

differential-audit 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/differential-audit/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Make agreement mean something

Two implementations agreeing proves they satisfy a prespecified contract. It does not prove either is correct, and it never validates the method or its assumptions. Both can be wrong in the same way — especially when one was written by reading the other. Design the comparison so that agreement is informative and disagreement is legible.

Rule: freeze before you compare; test the comparator before you trust it.

1. State the claim and the reference

Write down: what is being compared, which side is the reference, and what agreement would and would not establish. "Matches the R package" is a conformance claim, not a correctness claim. Say so explicitly, so nobody later reads parity as validation.

2. Freeze the inputs before inspecting anything

Record and fix: data versions or hashes, code and package versions, random seeds or realized sample splits, options and defaults, the outputs to be compared, and the acceptance thresholds. Freezing after a first look invites tolerance drift toward whatever the run produced.

Do not compare defaults across systems as if only the language changed. Map the choices explicitly — a "default" is a substantive modeling decision that usually differs between implementations.

3. Declare tolerance classes, and make them binding

Do not carry a single fuzzy epsilon. Classify each output:

  • EXACT — names, ordering, sample masks, counts, statuses, return/error codes, warning classes, option defaults. Byte-equal after documented normalization.
  • Scalar numeric — deterministic estimates, standard errors, p-values, critical values. State absolute and relative tolerances and the justification.
  • Matrix/vector — covariance matrices, influence summaries, weight vectors, plot data.
  • Stochastic — must meet a prespecified error-rate criterion with uncertainty reported.

A looser tolerance may be used only through a recorded approved divergence with a reason. Silent widening is the most common way a parity gate stops testing anything.

Read the full file on GitHub · 88 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 · 88 lines · 115 tokens per session scan A 72335e59883f

Subscribe to this mod's changes

differential-audit is a skill published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,567 stars, last pushed 14d ago), licensed MIT. It adds 115 tokens to every session and 1,266 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 2026-08-30.

Related

Other skills, from other repositories

paper-workflow

A staged workflow for producing an evidence-based economics or social-science research paper, from choosing a topic through submission. It coordinates existing tools and analysis options, including Python, Stata, and R.

brycewang-stanford/Paper-WorkFlow · 262 tokens

r-econometrics

Run IV, DiD, and RDD analyses in R with proper diagnostics.

brycewang-stanford/Auto-Empirical-Research-Skills · 20 tokens

econ-management-paper-polish

A writing and editing guide for papers in economics, management, finance, accounting, marketing, information systems, public administration, and related fields.

linkingoscar/econ-management-paper-polish · 83 tokens

did-causal

Use this Skill when the user needs to estimate causal treatment effects using difference-in-differences (DID) designs: two-way fixed effects (TWFE) regression, parallel trends pre-testing, Callaway-Sant'Anna staggered adoption estimator, and Goodman-Bacon decomposition. Covers both Python (linearmodels) and R (did…

xjtulyc/awesome-rosetta-skills · 75 tokens

test-native-extension

Validate a third-party control repo across four automated layers plus one printed manual recipe. Layer 1 asserts native-source structure (Android getName() and iOS +moduleName to manifest nativeModule; @ReactMethod / RCTEXPORTMETHOD to methods; no @ReactModule) plus load/init readiness (ReactPackage public no-arg…

microsoft/power-platform-skills · 211 tokens

test-site

Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.

microsoft/power-platform-skills · 46 tokens