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.
npx skills add VeryMath/AI4Math-Writing --skill claim-evidence-ledgergit clone --depth 1 https://github.com/VeryMath/AI4Math-WritingWrote 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.
[](https://agentmods.dev/skills/verymath/ai4math-writing/claim-evidence-ledger)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Extract claims from the target text.
- Classify each claim by mathematical, empirical, literature, or contribution role.
- Match claims to source evidence.
- 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-auditwhen needed. - Mark unsupported claims instead of rewriting them as if they were true.
- 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.
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.
- 10d ago First seen · 56 lines · 35 tokens per session scan A a60a39c8a59d
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.
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…
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…
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…
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.
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…
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…