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 agentmods add commands/llm4rocq/mathcomp-skills/mathcomp-reviewgit clone --depth 1 https://github.com/LLM4Rocq/mathcomp-skillsWrote 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/commands/llm4rocq/mathcomp-skills/mathcomp-review)<a href="https://agentmods.dev/commands/llm4rocq/mathcomp-skills/mathcomp-review"><img src="https://agentmods.dev/badge/commands/llm4rocq/mathcomp-skills/mathcomp-review.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.01946 |
| Opus 5 | $0.00009 | $0.00973 |
| Sonnet 5 | $0.00004 | $0.00389 |
| Haiku 4.5 | $0.00002 | $0.00195 |
Grade A, and why
mathcomp-review 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 4d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mathcomp-review
Read-only style review of math-comp / mathcomp-analysis Rocq (.v)
files. Runs the mechanical scanner, the SKILL.md Reviewer Checklist,
and axiom hygiene, then emits a structured punch list keyed to
reference.md section numbers.
Non-destructive: never edits, stages, or commits .v files. Every
finding is a CANDIDATE — the build is the oracle.
Usage
/mathcomp-review # changed .v files (git diff)
/mathcomp-review theories/foo.v # one explicit target
/mathcomp-review theories/*.v # several explicit targets
/mathcomp-review --scope=project # whole project (prompts first)
Inputs
| Arg | Required | Description |
|---|---|---|
| target | No | One or more .v files (or a directory) to review |
| --scope | No | changed (default), project, or implicit when targets set |
Defaults:
- No args →
--scope=changed(files modified since last commit). - One or more targets → review exactly those.
--scope=project→ review every tracked.v(requires confirmation).
Project-wide confirmation:
This will review every .v file in the project. Proceed? (yes / no)
Scope Behavior
- changed —
git diff --name-onlyandgit diff --name-only --cached, filtered to*.v. If empty, report "no changed .v files" and stop. - explicit targets — exactly the paths passed (glob-expanded by
the shell). Skip non-
.vand unreadable paths with a note. - project —
git ls-files '*.v'after the confirmation prompt.
The header of the report always echoes the resolved scope.
Actions
Run per resolved scope, naming the exact tool for each step.
-
Resolve scope — compute the target list (changed via
git diff --name-only| explicit targets |git ls-files '*.v'). -
Build status —
mcp__rocq-mcp__rocq_compile_fileon each target (file=<path>); surface any errors. If the rocq-mcp server is not configured/available, emit "build: skipped (rocq-mcp absent)" and continue — the rest of the review is static and does not depend on it. A broken build is reported but does not abort the review.
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.
- 4d ago First seen · 179 lines · 18 tokens per session scan A 8687ea8c9989
mathcomp-review is a command published in the GitHub repository LLM4Rocq/mathcomp-skills (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,946 once invoked, about $0.0001 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 commands, from other repositories
verify-math
Verify a self-authored mathematical result end to end by routing claims across adversarial review, numerical falsification, symbolic or CAS checks, and Lean, then aggregating one report. Use when a theorem, proposition, conjecture, or paper-wide mathematical argument needs the appropriate combination of verification…
master_analysis
Run comprehensive 5-phase analysis across labs, genetics, and protocols.
replication-package
Scaffold or audit a social-science replication package at a target directory, and audit the manuscript and its archived research objects against FAIR principles.
diff
Quantitative volume comparison between a CadQuery model and a reference STEP file.
arg-diagram
ARG academic-paper diagram mode — standalone structural & conceptual diagram generation.
simulation-calibrator
Test and refine simulation accuracy with validation loops, bias detection, and continuous improvement frameworks.