agentmods.dev

mathcomp-style-auditor

mathcomp-style-auditor is an agent for Claude Code from LLM4Rocq/mathcomp-skills. It costs 70 tokens per session (1,286 once invoked), scanned A, original, Apache-2.0.

A read-only reviewer for Rocq files that use the math-comp or mathcomp-analysis libraries. Rocq is a system for writing computer-checked mathematical proofs.

In plain words
What is it for?
It is for producing a structured list of style issues in one or more .v files, with findings tied to sections of the project’s style guide.
Why use it?
It finds style problems without changing, staging, or committing files, making parallel reviews safer.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: model in frontmatter.

Part of the mathcomp-skills plugin — 1 skill, 1 command, 1 agent, 1 hook shipped together

not rated 5repo changed 24d ago A scan 70 tokens original Apache-2.0

Good fit It is for producing a structured list of style issues in one or more .v files, with findings tied to sections of the project’s style guide.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/llm4rocq/mathcomp-skills/mathcomp-style-auditor
View source ↗ LLM4Rocq/mathcomp-skills
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.

Clone the repo
git clone --depth 1 https://github.com/LLM4Rocq/mathcomp-skills

Made for: Claude Code.

Or install mathcomp-skills, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent, 1 hook.

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 mathcomp-style-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/llm4rocq/mathcomp-skills/mathcomp-style-auditor/github.svg)](https://agentmods.dev/agents/llm4rocq/mathcomp-skills/mathcomp-style-auditor)
Your own site
<a href="https://agentmods.dev/agents/llm4rocq/mathcomp-skills/mathcomp-style-auditor"><img src="https://agentmods.dev/badge/agents/llm4rocq/mathcomp-skills/mathcomp-style-auditor/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 mathcomp-style-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/llm4rocq/mathcomp-skills/mathcomp-style-auditor"><img src="https://agentmods.dev/badge/agents/llm4rocq/mathcomp-skills/mathcomp-style-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,286 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 $0.00070 $0.01286
Opus 5.5 $0.00028 $0.00514
Sonnet 5.5 $0.00014 $0.00257
Haiku 4.5 $0.00007 $0.00129

Measured 24d ago against content hash 2d073cc33279, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mathcomp-style-auditor 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 24d 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.

agents/mathcomp-style-auditor.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mathcomp-style-auditor

You are an extra-critical math-comp / mathcomp-analysis reviewer auditing one .v file (or a small file-group). You are READ-ONLY: you have no Edit/Write tool and you never mutate the file, stage, or commit. You produce a structured punch list only. This is why the parent can safely fan out one instance per file in parallel — no two auditors ever write, so there is no same-file-overwrite race.

Inputs

  • The target .v file path(s).
  • The style guide ships with the skill: read ${CLAUDE_SKILL_DIR}/reference.md (sections 22–33 in particular for fresh-maintainer feedback) and ${CLAUDE_SKILL_DIR}/playbook.md § "Audit recommendations that don't pan out".

Actions

  1. Mechanical first — run the bundled scanner and fold its output into your punch list:

    ${CLAUDE_SKILL_DIR}/scripts/audit-quick.sh <file>

    Use Read/Grep to inspect the file directly; do not write scripts or temp files just to view source.

  2. Optional live checks (read-only; skip silently if rocq-mcp is absent — never invoke MCP tool names via Bash):

    • mcp__rocq-mcp__rocq_compile_file file=<path> — confirm the file compiles, so you can mark whether findings are on a green build.
    • mcp__rocq-mcp__rocq_query command="Search …" / "About …" / "Print Assumptions …" — confirm a name exists / its spelling / its axioms before asserting a naming or hygiene finding.

  3. Enumerate every style violation and key each to a reference.md section number. Categories to cover:

    • §1, §6, §22.3 — line length, scope delimiters
    • §3 — imports: all_boot all_order, not deprecated all_ssreflect
    • §3, §23 — fully-qualified module names
    • §8, §26 — proof terminator hygiene
    • §9 — tactic spacing
    • §10–§14 — naming
    • §16, §31 — Arguments / implicits
    • §22.1–22.4 — concision / triviality
    • §24 — type constraint hygiene
    • §25 — @ discipline
    • §26.5, §27.9 — bullets are inert (not checked); goal selectors
    • §27 — bookkeeping idioms
    • §27.11 — clear / refine a hypothesis in place with {}H
    • §28 — case analysis
    • §28.1 — nat case splits: leqP/ltnP/ltngtP, not leP/ltP
    • §29 — rewriting idioms
    • §32 — Definition vs. Notation, is_ prefix on operators
    • §36.2 — deprecated structure names (ringType → nzRingType/Pz)
    • §48 — mathcomp 1 / MCB idioms (EqMixin, [eqType of T], Canonical … Pack) → HB / mathcomp 2.5 forms

Read the full file on GitHub · 111 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. 24d ago Changed · +9 lines 2d073cc33279
  2. 1mo ago First seen · 102 lines · 70 tokens per session scan A 705467731153

Subscribe to this mod's changes

mathcomp-style-auditor is an agent published in the GitHub repository LLM4Rocq/mathcomp-skills (5 stars, last pushed 25d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,286 once invoked, about $0.0003 per session on Opus 5.5. 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.

Code reviewScientific
Related

Other agents, from other repositories

algorithm-reviewer

Use when code contains non-trivial algorithms, loops, recursion, or data-structure choices — the specialist that analyzes the time/space complexity (Big-O) of every routine and proposes a lower-complexity algorithm or data structure where one exists. Verifies against the performance and scientific persona standards.

jeremylongshore/tons-of-skills-marketplace · 64 tokens

r-reviewer

R code reviewer for academic scripts. Checks code quality, reproducibility, figure generation patterns, and theme compliance. Use after writing or modifying R scripts.

pedrohcgs/claude-code-my-workflow · 34 tokens

r-reviewer

R code reviewer for academic scripts. Checks code quality, reproducibility, figure generation patterns, and theme compliance. Use after writing or modifying R scripts.

brycewang-stanford/Auto-Empirical-Research-Skills · 34 tokens

meteo-reviewer

Reviews a weather event analysis, synoptic narrative, or atmospheric mechanism claim for meteorological rigor — dynamical and thermodynamic consistency, physical basis, observational adequacy, competing drivers, hydrological consistency, and uncertainty calibration. Grounded in AMS CCM-level competence across the five…

dgilford/ai-science-toolkit · 115 tokens

debugger

Diagnose a repeated gate or slice-verify failure via bounded scientific-method hypothesis cycles, auto-invoked before the retry budget is spent.

Koroqe/claude-code-sdlc · 30 tokens

paper-reviewer

Adversarial reviewer agent for the AI co-mathematician system. Gates workstream completion — a workstream cannot be marked complete until paper-reviewer writes an explicit approval file. Cross-checks references resolve, that proofs have no leftover \unproven blocks (or are properly flagged), that code outputs match…

morankor/theorist-toolbox · 112 tokens