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 proof-obligation-and-assumption-auditgit 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/proof-obligation-and-assumption-audit)<a href="https://agentmods.dev/skills/verymath/ai4math-writing/proof-obligation-and-assumption-audit"><img src="https://agentmods.dev/badge/skills/verymath/ai4math-writing/proof-obligation-and-assumption-audit/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/proof-obligation-and-assumption-audit"><img src="https://agentmods.dev/badge/skills/verymath/ai4math-writing/proof-obligation-and-assumption-audit.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 | $0.00043 | $0.00527 |
| Opus 5 | $0.00022 | $0.00264 |
| Sonnet 5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
proof-obligation-and-assumption-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 11d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proof Obligation And Assumption Audit
Audit whether a mathematical result is supported by its stated assumptions, dependencies, and proof coverage. This is a writing review, not automated theorem proving: it identifies obligations and risks that paper prose must not hide.
Inputs
- Theorem, proposition, lemma, corollary, algorithm guarantee, or experiment claim under review.
- Proof sketch or proof text, definitions, notation ledger, cited external results, and relevant source notes.
- Optional venue standards or reviewer comments.
If proof material is unavailable, mark the result provisional instead of rewriting it as proved.
Output Contract
Return a proof-obligation table with:
| Field | Meaning |
|---|---|
result |
The theorem, lemma, proposition, or claim under review |
assumptions |
Quantifiers, domains, regularity, constraints, and boundary conditions |
dependencies |
Definitions, previous results, external theorems, experiments, or algorithms used |
obligation |
What the proof must establish or verify |
coverage |
covered, partial, missing, conflicting, or unclear |
risk |
Meaning-preserving issue, missing case, overclaim, citation-fit risk, or notation risk |
action |
Keep, soften, split, add assumption, cite precisely, prove, verify, or ask human |
Workflow
- Restate the result with all quantifiers, domains, and assumptions visible.
- List proof obligations: existence, uniqueness, invariance, convergence, optimality, bounds, limiting cases, case splits, and dependency conditions.
- Check every cited external theorem against its original assumptions and conclusion strength when sources are available.
- Compare proof coverage to obligations; mark missing or partial cases without patching the mathematics.
- Suggest wording changes only when they preserve the verified mathematical meaning.
Review Rules
- Do not strengthen a theorem to match the desired contribution.
- Do not weaken or drop assumptions without checking proof dependencies.
- Keep empirical evidence, heuristic arguments, conjectures, and formal proof status separate.
- Route notation conflicts to
notation-and-variable-consistencybefore making semantic judgments that depend on symbols or dimensions.
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.
- 11d ago First seen · 58 lines · 43 tokens per session scan A 805b867a1a42
proof-obligation-and-assumption-audit is a skill published in the GitHub repository VeryMath/AI4Math-Writing (6 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 527 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
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…
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…
mixed-integer-programming
Models and solves mixed-integer linear programs, including binary, integer, and continuous decision variables with linear objectives and constraints.
or-solver
Configure the Python environment for a solver already specified by the user or a modeling skill. Check the target interpreter and dependencies, install required packages, configure licenses and environment variables, troubleshoot setup errors, and report availability. Use for installing or repairing a named solver…
ai4math-optimization
Route AI4Math optimization tasks to the appropriate bundled skill package.