proof-derivation-forensics

proof-derivation-forensics is a skill for Claude Code from wenhaochai/claude-plugins. It costs 222 tokens per session (13,674 once invoked), scanned A, a copy of proof-derivation-forensics, MIT.

A review tool for checking whether someone else's written mathematical proof or derivation actually supports its stated theorem. It looks for skipped obligations, circular reasoning, invalid steps, changed symbol meanings, and unstated assumptions.

In plain words
What is it for?
Use it to audit research proofs and mathematical derivations, with findings tied to specific passages.
Why use it?
It helps reveal substantive flaws that can make a theorem unsupported, even when the writing looks plausible. The findings are evidence for a later verdict rather than the verdict itself.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the anti-autoresearch plugin — 12 skills shipped together

Good fit Use it to audit research proofs and mathematical derivations, with findings tied to specific passages.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add wenhaochai/claude-plugins
Claude Code
/plugin install anti-autoresearch

Made for: Claude Code.

Or install anti-autoresearch, the plugin that ships this one along with the rest of its 12 skills.

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 proof-derivation-forensics

README.md
[![agentmods](https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/proof-derivation-forensics/github.svg)](https://agentmods.dev/skills/wenhaochai/claude-plugins/proof-derivation-forensics)
Your own site
<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/proof-derivation-forensics"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/proof-derivation-forensics/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 proof-derivation-forensics

Your own site · 80×15
<a href="https://agentmods.dev/skills/wenhaochai/claude-plugins/proof-derivation-forensics"><img src="https://agentmods.dev/badge/skills/wenhaochai/claude-plugins/proof-derivation-forensics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 222 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,674 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 98% copy Near-identical to another mod 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 $0.00222 $0.13674
Opus 5 $0.00111 $0.06837
Sonnet 5 $0.00044 $0.02735
Haiku 4.5 $0.00022 $0.01367

Measured 9d ago against content hash 922998e6dbd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

proof-derivation-forensics 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 9d 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.

Origin

This is a copy

98% identical to proof-derivation-forensics — 47 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

anti-autoresearch/skills/proof-derivation-forensics/SKILL.md · 817 lines

How it starts

The opening of the file, as written. The whole thing — 817 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proof & Derivation Forensics — does the written proof hold?

Audit family G (proof & derivation integrity) for: $ARGUMENTS (requires claims.json from /evidence-ledger). A fresh cross-model reviewer reads each theorem/proof and proposes span-anchored findings; this skill writes proof-derivation-forensics.findings.json. The deterministic adjudicator — not this skill — computes the verdict.

🔒 Do not wrap this skill in /loop, /schedule, or CronCreate. It is verdict-bearing input — it proposes the findings the deterministic adjudicator turns into the report. Re-firing it on a wall-clock timer adds no signal: its output changes only when the paper / ledger changes, not with the clock. Schedule the external wait that precedes it — ledger built → audit once. (Mirrors ARIS's external-cadence doctrine.)

Broken math is the single most-cited "obviously machine-written" tell in real reviews ("过不去的步骤用文字糊弄", "车轱辘话复述当证明", "关键公式符号用反"). Unlike the surface signals of family F, family-G flaws are substantive and can be critical: a theorem whose proof is circular, skips a load-bearing obligation, or takes an invalid step does not support its claim. And — crucially — proof validity is decidable from the written proof: we never need the code or results, so family G is verdict-bearing at L1 (the LaTeX source) and can still reach HARD_FLAGS with no repo — but needs that source, because PDF-extracted math is unreliable; at an L0 (PDF-only) run a family-G flaw surfaces as info only. Adapted from ARIS proof-checker (per-obligation ledger + 20-category taxonomy + counterexample red team) and formula-derivation (identity/proposition/approximation/interpretation step typing), reframed from "fix my own proof" to "audit a third party's proof, detect-only." There is no fixing here and no authorship verdict — only "the step shown does not hold," with the exact line quoted.

Why this exists

An autoresearch pipeline (or a rushed human) writes a theorem statement, then a proof, then an abstract that advertises the theorem — in separate passes, never reconciled at the level of the argument. The result is a proof that does not establish its own claim:

Read the full file on GitHub · 817 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. 9d ago First seen · 817 lines · 222 tokens per session scan A 922998e6dbd8

Subscribe to this mod's changes

proof-derivation-forensics is a skill published in the GitHub repository wenhaochai/claude-plugins (16 stars, last pushed 8d ago), licensed MIT. It adds 222 tokens to every session and 13,674 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to proof-derivation-forensics, differing in 47 lines, and is treated as a copy.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens