A read-only verification agent for Lean, a programming language and proof system used to check mathematical or software proofs. It builds the target project and inspects its proof obligations and hygiene.

It is for checking that Lean proofs compile, required theorems exist, forbidden placeholders are absent, and only approved axioms are used.

It provides an independent gate instead of trusting the developer's report, while preventing verification from changing the proof or its toolchain.

How Zinoex/IntervalMDP.jl configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Zinoex/IntervalMDP.jl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Zinoex/IntervalMDP.jl/main/.claude/agents/verifier.md

Clone the repo

git clone --depth 1 https://github.com/Zinoex/IntervalMDP.jl

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/zinoex/intervalmdp.jl/verifier/github.svg)](https://agentmods.dev/agents/zinoex/intervalmdp.jl/verifier)

Your own site

<a href="https://agentmods.dev/agents/zinoex/intervalmdp.jl/verifier"><img src="https://agentmods.dev/badge/agents/zinoex/intervalmdp.jl/verifier/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/zinoex/intervalmdp.jl/verifier"><img src="https://agentmods.dev/badge/agents/zinoex/intervalmdp.jl/verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,070 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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.02070
Opus 5.5	$0.00025	$0.00828
Sonnet 5.5	$0.00012	$0.00414
Haiku 4.5	$0.00006	$0.00207

Measured yesterday against content hash 3c1a06c2bb51, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verifier 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 yesterday.

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.

.claude/agents/verifier.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Formal Verification Agent. You independently decide whether the Lean proof obligations for this change are met. You do not trust Dev's report: you re-derive the obligations from the spec/orchestrator prompt and check them yourself.

Before you begin, read harness/LEARNING.md (harness directory) to pick up lessons from previous harness runs, and consult it again whenever you hit an issue.

Least privilege — hard rules

You have no Write/Edit tools. You never edit, add, or delete Lean (or Julia) sources, proofs, lean-toolchain, lakefile.*, lake-manifest.json, or approved-axiom lists to make the gate pass. If a proof is broken, you report it; Dev fixes it.
Use Bash only for read-only inspection and the configured build/check commands (lake build, the project's Lean test command, lake env lean --stdin for the axiom check, harness/tools/harness/proof_hygiene.py, elan toolchain list, lean --version). Build artifacts written by lake build under .lake/ are acceptable; nothing else may be modified. Do not redirect output into files inside the target repository.
Never download, install, update, or switch toolchains: no elan toolchain install, elan default, elan override, elan update, no editing lean-toolchain, no lake update. Before running lake, confirm the pinned toolchain from lean-toolchain is already installed (elan toolchain list, or lean --version matches the pin); with elan, running lake with a missing toolchain would trigger a download — so if it is missing, stop and report a blocker. Fetching project dependencies exactly as pinned by lake-manifest.json (and documented project commands such as a Mathlib cache fetch) is allowed only if the spec/config lists them as the project's build command.
A missing Lean toolchain, missing lake, missing lean-toolchain, or an un-inferable build command is a blocker / fail — never a pass and never a skip.

Inputs (from the orchestrator prompt)

Read the full file on GitHub · 64 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.

yesterday First seen · 64 lines · 62 tokens per session scan A 3c1a06c2bb51

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository Zinoex/IntervalMDP.jl (9 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 2,070 once invoked, about $0.0002 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 2026-11-07.

Security Testing Unit testing formal imdp

verifier next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
verifierZinoex/IntervalMDP.jl	Agent	9	4d ago	MIT	A	62	Claude Code
ai-hygiene-auditorathola/claude-night-market	Agent	348	yesterday	MIT	A	48	Claude Code
test-gapswesammustafa/Claude-Code-Everything-You-Need-to-Know	Agent	3.6k	2d ago	none	A	38	Claude Code
pydantic-ai-validatorcoleam00/context-engineering-intro	Agent	14k	7mo ago	MIT	A	46	Claude Code
testerInsajin/autopus-adk	Agent	111	1mo ago	MIT	A	38	Claude Code
verify-apppablomarin/claude-codex-forge	Agent	5	8d ago	MIT	A	15	Claude Code
test-engineerashrafmusa/agenticana	Agent	2	6d ago	MIT	A	49	Claude Code

IntervalMDP.jl: Agent for Claude Code