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 instructions/scidonia/rocq-piler/agents-mdgit clone --depth 1 https://github.com/scidonia/rocq-pilerWrote 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/instructions/scidonia/rocq-piler/agents-md)<a href="https://agentmods.dev/instructions/scidonia/rocq-piler/agents-md"><img src="https://agentmods.dev/badge/instructions/scidonia/rocq-piler/agents-md.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 5.1 | $0.00706 | $0.00706 |
| Opus 5 | $0.00353 | $0.00353 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
rocq-piler AGENTS.md 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 5d 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.
rocq-piler
MCP server providing interactive Coq/Rocq proof development tools via coq-lsp.
Rules
- Prove, don't research. Start writing proofs immediately. Don't search the web for existing proofs or spend time reading the file and understanding the architecture. If a lemma fails, check the error and iterate.
- Use
edit_filefor all edits. It reports errors with goal states inline — you don't need bash+coqc. - Start with easy lemmas (extends, store weakening) — not the hardest (shift, substitution).
Tools
search_lemmas— find relevant lemmas in the Coq environment by name or patternedit_file— write or modify.vfiles (supportsfind/replaceor range-based edits)check_file— verify the file and report errors with diagnostic messages and goal states. Supportsmode: "errors"(compact: only failures/admitted) andmode: "first"(one error at a time)focus_proof— inspect proof state: goals, bullet stack, admitsstratify— case-split a proof and auto-close easy casesclose_admits— batch-close surviving admits with a portfolio of tacticsreset_proof— wipe a proof body and start fresh
Most non-trivial proofs need helper lemmas (e.g. substitution, weakening, inversion). Add them before the main theorem.
Start with the easy lemmas first (extends, store weakening, heap operations) — not the hardest (shift, substitution). Build up gradually. If a lemma takes more than a few tries, reset and try a different approach. If a proof has too many cases to write by hand, use stratify to split it and close_admits to batch-close survivors.
Never reference auto-generated names from destruct, inversion, or induction. Coq-lsp and coqc can produce different names for the same proof. Always use as clauses (destruct H as [x y], inversion H as [pattern], induction H as [IH]) and subst to canonicalize. Avoid rename.
Build & Test
npm run build # TypeScript compilation
npm test # Run test suite
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.
- 5d ago First seen · 56 lines · 706 tokens per session scan A 44643723fe2f
rocq-piler AGENTS.md is an instructions file published in the GitHub repository scidonia/rocq-piler (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 706 tokens to every session, about $0.0035 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).