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/schildep/verified-polygon-intersection/claude-mdgit clone --depth 1 https://github.com/schildep/verified-polygon-intersectionWrote 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/schildep/verified-polygon-intersection/claude-md)<a href="https://agentmods.dev/instructions/schildep/verified-polygon-intersection/claude-md"><img src="https://agentmods.dev/badge/instructions/schildep/verified-polygon-intersection/claude-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 | $0.00746 | $0.00746 |
| Opus 5 | $0.00373 | $0.00373 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
verified-polygon-intersection CLAUDE.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 3d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This development formalizes polygon intersections.
Guideline on placement of definitions/theorems
Polygons/Defs.lean and Polygons/Datastructures.lean contain exactly the definitions necessary to state the main specifications Polygons/MultipolygonIntersectionAlgorithm.lean, Polygons/MultipolygonIntersectionAlgorithmWithPreconditionCheck.lean.
Beyond that, files in Polygons/ follow a three-level hierarchy. For each topic X:
Polygons/X.lean— top of hierarchy for topicX. Restates definitions or characterizes definitions and restates theorems that are worth exporting for topicX. This is setup such that a reviewer only needs to reviewPolygons/X.leanto completely understand definitions and theorem statement from the associated files and when the implementation changes, the filePolygons/X.leandoes not need to change.- Contains user-facing definitions with either their full definition statement
or their unique characterizations (a
defthat defers toXImplplus a theorem that uniquely characterizes it). In either case this involves a new definition in theXnamespace. - Contains theorem statements of theorems worth exporting, with proofs
referring to
XProofs. - Theorem statements in
Polygons/X.leannever should refer to definitions fromXImplorXProofs, instead they should refer to the counterparts defined inPolygons/X.lean. - Never contains a proof; instead refers to a copy of the theorem stated
in
XProofs.lean. Even short proofs go toXProofs, so future proof rewrites do not touch the top-of-hierarchy file. - Never contains an implementation. Instead refer to
XImpl. - Never contains definitions or helper theorems that will only be used
in
XProofs.leanorXImpl.lean.
- Contains user-facing definitions with either their full definition statement
or their unique characterizations (a
Polygons/XImpl.lean— runtime implementation. Contains the computabledefs that are called in the runtime path of the algorithm. Mathlib-free so it can be initialized in the WASM binary without dragging the tactic chain in. Does not containdefs that are not (directly or indirectly) called in the runtime path.Polygons/XProofs.leanrestatement and proofs of theorems inXand private helper definitions and theorems. Free to use Mathlib and tactics. Dead-code eliminated out of the WASM binary because noXImplinitializer references it.
It is important that you follow this guideline when adding definitions or theorems.
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.
- 3d ago First seen · 57 lines · 746 tokens per session scan A 2c44e45a20ac
verified-polygon-intersection CLAUDE.md is an instructions file published in the GitHub repository schildep/verified-polygon-intersection (46 stars, last pushed 3mo ago), licensed MIT. It adds 746 tokens to every session, about $0.0037 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 2026-08-30.
Other instructions, from other repositories
VCVio AGENTS.md
Instructions for Verified-zkEVM/VCVio, covering vcvio — ai agent guide, fast start, attribution, headers, and docstrings, module scopes and what this project is.
leanforge-mcp CLAUDE.md
Claude Code instructions for sandraschi/leanforge-mcp, covering claude.md -- leanforge-mcp, what this repo does, key concepts, when working on agent.py and when working on leanclient.py.
formal CLAUDE.md
Instructions for yamafaktory/formal, covering formal, rust, the files that judge changes, hints and lean.
sounio copilot-instructions.md
Instructions for Sounio-lang/sounio, covering sounio language instructions for github copilot, compiler, critical syntax differences from rust, effects system (required) and variables and types.
leanforge-mcp AGENTS.md
AGENTS.md instructions for sandraschi/leanforge-mcp, covering agents.md -- leanforge-mcp, stack, repo layout, critical rules and lean subprocess.
shannon-prover CLAUDE.md
Claude Code instructions for SkyShannonProver/shannon-prover, covering shannon prover: claude entry point, current boundary, easycrypt environment, eval safety and current documentation.