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.
git clone --depth 1 https://github.com/frenzymath/ArchonWrote 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/plugins/frenzymath/archon/lean4)<a href="https://agentmods.dev/plugins/frenzymath/archon/lean4"><img src="https://agentmods.dev/badge/plugins/frenzymath/archon/lean4/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.
<a href="https://agentmods.dev/plugins/frenzymath/archon/lean4"><img src="https://agentmods.dev/badge/plugins/frenzymath/archon/lean4.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
lean4 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 1mo 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.
What it actually says
{
"name": "archon-lean4",
"version": "4.4.0",
"description": "Archon's modified Lean 4 plugin (draft, formalize, autoformalize, prove, autoprove, checkpoint, review, refactor, golf, learn, doctor) — forked from cameronfreer/lean4-skills",
"author": {"name": "Cameron Freer", "email": "[email protected]"}
}
What it installs
The manifest is a name and a version. 1 skill, 11 commands, 4 agents, 3 hooks travel with it, and installing the plugin installs all of them — 404 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill lean4 A 112 tokens
- Command learn A 8 tokens
- Command autoprove A 14 tokens
- Command review A 9 tokens
- Command formalize A 11 tokens
- Command prove A 12 tokens
- Command draft A 10 tokens
- Command autoformalize A 14 tokens
- Command checkpoint A 9 tokens
- Command doctor C 9 tokens
- Command golf A 17 tokens
- Command refactor A 14 tokens
- Agent lean4-proof-golfer A 47 tokens
- Agent lean4-axiom-eliminator A 44 tokens
- Agent lean4-proof-repair A 37 tokens
- Agent lean4-sorry-filler-deep A 37 tokens
- Hook PostToolUse A not measured
- Hook PreToolUse A not measured
- Hook SessionStart A not measured
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.
- 1mo ago First seen · 7 lines scan A 5d55e02656b7
lean4 is a plugin published in the GitHub repository frenzymath/Archon (225 stars, last pushed 2mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
nvidia-cuopt-skills
Agent skills for NVIDIA cuOpt: routing (VRP, TSP, PDP), LP/MILP/QP, installation (Python/C/developer), and REST server. Use when building or solving optimization with cuOpt.
writing-lean-proofs
Structured Lean 4 proof writing and library design following Mathlib conventions.
powergridmodel
power-grid-model Python skill - high-performance steady-state distribution power system analysis: power flow, state estimation, and IEC 60909 short-circuit calculations with 22 component types and batch/parallel computation.
write-lean-code
Lean 4 and Mathlib conventions for code, proofs, naming, documentation and compile-time tests that mirror the public library API.
stata-c-plugins
Develop high-performance C/C++ plugins for Stata — SDK setup, .ado wrappers, cross-platform compilation, performance optimization, and Python/R package translation.
numerical
Numerical computing verification and optimization agent for Python/Dart ndarray, tensor, and scientific computing codebases.