claim-evidence-ledger

claim-evidence-ledger is a skill for Claude Code, Codex from VeryMath/AI4Math-Writing. It costs 35 tokens per session (500 once invoked), scanned A, original, MIT.

A review method for checking whether claims in a mathematical paper are supported. It links each claim to evidence such as a proof, experiment, citation, or stated uncertainty.

In plain words
What is it for?
Auditing paper drafts, tracking claim support, recording the location and status of each claim, and suggesting whether to keep, cite, soften, remove, or verify it.
Why use it?
It helps find unsupported statements, missing citations, incomplete proofs, and claims that say more than the evidence shows. If source material is missing, it requests that evidence instead of filling the gaps.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Auditing paper drafts, tracking claim support, recording the location and status of each claim, and suggesting whether to keep, cite, soften, remove, or verify it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/verymath/ai4math-writing/claim-evidence-ledger
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 VeryMath/AI4Math-Writing --skill claim-evidence-ledger
Clone the repo
git clone --depth 1 https://github.com/VeryMath/AI4Math-Writing

Made for: Claude Code, Codex.

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 claim-evidence-ledger

README.md
[![agentmods](https://agentmods.dev/badge/skills/verymath/ai4math-writing/claim-evidence-ledger/github.svg)](https://agentmods.dev/skills/verymath/ai4math-writing/claim-evidence-ledger)
Your own site
<a href="https://agentmods.dev/skills/verymath/ai4math-writing/claim-evidence-ledger"><img src="https://agentmods.dev/badge/skills/verymath/ai4math-writing/claim-evidence-ledger/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 claim-evidence-ledger

Your own site · 80×15
<a href="https://agentmods.dev/skills/verymath/ai4math-writing/claim-evidence-ledger"><img src="https://agentmods.dev/badge/skills/verymath/ai4math-writing/claim-evidence-ledger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 500 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 $0.00035 $0.00500
Opus 5 $0.00017 $0.00250
Sonnet 5 $0.00007 $0.00100
Haiku 4.5 $0.00003 $0.00050

Measured 10d ago against content hash a60a39c8a59d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claim-evidence-ledger 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.

skills/paper-writing/skills/claim-evidence-ledger/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claim Evidence Ledger

Build a claim ledger before polishing prose. The goal is to make every substantive statement traceable to a proof, experiment, citation, or explicit uncertainty.

Inputs

  • Paper draft or target section.
  • Source packet: theorem statements, proof notes, experiment logs, figures, bibliography, related-work notes, reviewer comments, or prior drafts.
  • Optional venue/audience constraints and citation policy.

If sources are missing, request the source packet or produce only an evidence request.

Output Contract

Return a table with:

Field Meaning
claim The exact or paraphrased paper claim
location Section, paragraph, theorem, figure, or equation
type theorem, proof, experiment, citation, positioning, limitation, future-work
support Source file, theorem, log, citation key, or reviewer comment
status supported, citation-needed, needs-proof, needs-experiment, overclaimed, unsupported, uncertain
action Keep, cite, soften, remove, verify, or ask human

Workflow

  1. Extract claims from the target text.
  2. Classify each claim by mathematical, empirical, literature, or contribution role.
  3. Match claims to source evidence.
  4. For mathematical claims, distinguish "has a proof sketch" from "assumptions, dependencies, and proof obligations have been audited"; route the latter to proof-obligation-and-assumption-audit when needed.
  5. Mark unsupported claims instead of rewriting them as if they were true.
  6. Suggest edits that preserve the strongest source-backed version.

Review Rules

  • Do not invent citation keys, theorem numbers, experiments, or author claims.
  • Keep theorem/proof status distinct from conjecture, heuristic, or empirical evidence.
  • Do not mark a theorem claim fully supported when assumptions, dependency fit, or edge cases are still unaudited.
  • Treat abstract, introduction, and conclusion claims as high risk because they compress and often overstate results.

Read the full file on GitHub · 56 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 · 56 lines · 35 tokens per session scan A a60a39c8a59d

Subscribe to this mod's changes

claim-evidence-ledger is a skill published in the GitHub repository VeryMath/AI4Math-Writing (6 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 500 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

or-solver

Unified solver detection, installation, selection, and license configuration for OR optimization skills (LP, MIP, SOCP). One-stop solver management: detect installed packages, install missing solvers with proper priority, select the best available solver by problem type, and troubleshoot common errors. Covers 20…

VeryMath/AI4Math-Optimization · 145 tokens

cdopt-optimization

Use when Codex needs to solve, reproduce, test, compare, generate examples for, or diagnose CDOpt manifold optimization workflows, including CDOpt package smoke tests, official problem description cards, Stiefel dictionary learning, SciPy wrappers, PyTorch/JAX/NumPy CDOpt examples, dependency checks, tiny CPU…

VeryMath/AI4Math-Optimization · 80 tokens

linear-programming

Models and solves linear programs (LP) with multiple solvers (COPT, Gurobi, MOSEK, CPLEX, HiGHS (scipy/highspy), CLARABEL, PuLP/CBC, CVXOPT, OR-Tools/GLOP, GLPK, SoPlex, lpsolve, ECOS). Restates natural-language word problems into LP before building and solving. When no local solver is available, searches GitHub for…

VeryMath/AI4Math-Optimization · 149 tokens

copt-linear-program

A tool for turning linear programming problems into mathematical models and solving them with Cardinal Optimizer, a software package for optimization. It can start from a word problem or from supplied matrices and JSON data.

VeryMath/AI4Math-Optimization · 90 tokens

osqp-solver

Model, solve, update, reproduce, and diagnose continuous convex quadratic programs with the OSQP Python interface, including canonical-form conversion, sparse CSC data, solver-status gates, residual checks, infeasibility certificates, warm starts, repeated parametric QPs, and academic citation. Use when a task names…

VeryMath/AI4Math-Optimization · 131 tokens

second-order-cone-programming

Models and solves second-order cone programs and problems convertible to SOCP form using cvxpy with multiple solver backends (COPT, Gurobi, MOSEK, CPLEX, CLARABEL, ECOS, SCS, CVXOPT, COSMO, OSQP). Handles linear objectives with second-order cone constraints, as well as problems reducible to SOCP such as portfolio…

VeryMath/AI4Math-Optimization · 114 tokens