agentmods.dev

writing-rocq-proofs

writing-rocq-proofs is a skill for Claude Code, Codex from OutlineDriven/odin-claude-plugin. It costs 50 tokens per session (1,226 once invoked), scanned A, original, Apache-2.0.

A skill for writing and maintaining Rocq proofs. Rocq is a proof assistant, formerly called Coq, that lets you check mathematical statements with computer-verified proofs.

In plain words
What is it for?
Use it to create or review `.v` proof files, migrate an older Coq project, update build files, and compile the project under the chosen Rocq version.
Why use it?
It provides a defined process for Rocq 9.x work and Coq-to-Rocq migrations, including project builds and checking which assumptions a theorem uses.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the odin-formal plugin — 9 skills shipped together

not rated 35repo yesterday A scan SkillSpector: pass 50 tokens original Apache-2.0

Good fit Use it to create or review .v proof files, migrate an older Coq project, update build files, and compile the project under the chosen Rocq version.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outlinedriven/odin-claude-plugin/writing-rocq-proofs
View source ↗ OutlineDriven/odin-claude-plugin outlinedriven.github.io
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 OutlineDriven/odin-claude-plugin --skill writing-rocq-proofs
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-claude-plugin

Made for: Claude Code, Codex.

Or install odin-formal, the plugin that ships this one along with the rest of its 9 skills.

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 writing-rocq-proofs

README.md
[![agentmods](https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/writing-rocq-proofs/github.svg)](https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/writing-rocq-proofs)
Your own site
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/writing-rocq-proofs"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/writing-rocq-proofs/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 writing-rocq-proofs

Your own site · 80×15
<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/writing-rocq-proofs"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/writing-rocq-proofs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,226 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00050 $0.01226
Opus 5 $0.00025 $0.00613
Sonnet 5 $0.00010 $0.00245
Haiku 4.5 $0.00005 $0.00123

Measured 4d ago against content hash cd3111a0221e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

writing-rocq-proofs 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.

plugins/odin-formal/skills/writing-rocq-proofs/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Rocq proofs

Contract

Field Bound contract
Trigger The task is to write, review, or maintain Rocq 9.x proofs, or to migrate a legacy Coq codebase through the Coq to Rocq rename. Methodology stays with proof-driven.
Authority Reversible local: writes only Rocq source files, project build files such as _CoqProject and opam files inside the target project, and scoped mechanical Rocq checks; rollback is version control. No remote mutation.
Side effect Local writes to .v sources, project build files, and migration edits. No remote mutation.
Done The project compiles under the pinned Rocq version, and Print Assumptions on each delivered theorem lists only the axioms the project declares.

Inputs

  • Rocq 9.2.0, the current release of a monthly cadence that started with 9.0.0 in March 2025, installed with opam install rocq-prover.9.2.0 or as the Rocq Platform bundle. Docs: rocq-prover.org.
  • A proof environment: VsCoq (the official VS Code extension) or Proof General for Emacs, or rocq repl.
  • The .v sources and theorem statements; for a migration, the legacy Coq project.
  • Build facts: source files keep the .v extension, rocq compile emits .vo files that are specific to the compiling Rocq version, and -Q directory dirpath maps a directory to a logical prefix so Require resolves.

Procedure

  1. Pin the toolchain and open the proof loop. Install the pinned version with opam install rocq-prover.<version>, and prove in rocq repl or an editor session with VsCoq or Proof General. Compile with rocq compile file.v; for a project, generate a Makefile with rocq makefile -f _CoqProject -o CoqMakefile, where _CoqProject lists sources and -Q/-R mappings. Done when: the repl or editor runs against the project's pinned version and a Require of project code resolves.
  2. State the skeleton before proving. Write the target theorem and every helper lemma with its body closed by Admitted, and compile: the skeleton type-checks while each Admitted marks an independent work unit. Separate subgoals with focused bullets so each stays addressable. Done when: the skeleton compiles and every Admitted is an identified work unit.
  3. Fill proofs one goal at a time. Introduce the context with intros, decompose with destruct and induction, transform with rewrite and apply, and close with a terminal step such as exact or reflexivity. Prefer structured steps over long apply chains, and close every finished proof with Qed. Done when: every Admitted is replaced by a proof that closes with Qed.
  4. Audit the axiom footprint. Run Print Assumptions <theorem> on each delivered theorem: it displays the axioms, parameters, and variables the theorem depends on. An Admitted helper or an Axiom declaration appears in that output, so the kernel report is the gate, not a text search. Done when: each delivered theorem's footprint matches the declared axioms and no Admitted remains.
  5. Migrate a legacy Coq project. Rename the opam dependency: coq is replaced by rocq-core, the prover ships as rocq-prover, and ported packages take rocq-* names. Rewrite From Coq Require Import X to From Stdlib Require Import X, because the Coq.* standard-library namespace became Stdlib.* in 9.0. Compile and fix each deprecation at its site: 9.1 added the modular integer arithmetic theory with about 450 lemmas and deprecates the Rtauto and rtauto.Bintree plugins. The legacy coqc, coqtop, and coq_makefile shims still exist in 9.x; remove calls to them as the migration lands. Done when: the project builds under the pinned Rocq 9.x with rocq-* package names, Stdlib imports, and no deprecation warning on delivered files.

Read the full file on GitHub · 39 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 39 lines · 50 tokens per session scan A cd3111a0221e

Subscribe to this mod's changes

writing-rocq-proofs is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 1,226 once invoked, about $0.0003 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 2026-09-06.

Claude CodeScientificclaude-code-pluginclaude-code-pluginsclaude-marketplaceclaude-pluginsoutline-driven-development
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens