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 skills add sandraschi/leanforge-mcp --skill lean_expertgit clone --depth 1 https://github.com/sandraschi/leanforge-mcpWrote 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/skills/sandraschi/leanforge-mcp/lean_expert)<a href="https://agentmods.dev/skills/sandraschi/leanforge-mcp/lean_expert"><img src="https://agentmods.dev/badge/skills/sandraschi/leanforge-mcp/lean_expert/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/skills/sandraschi/leanforge-mcp/lean_expert"><img src="https://agentmods.dev/badge/skills/sandraschi/leanforge-mcp/lean_expert.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01228 |
| Opus 5.5 | $0.00000 | $0.00491 |
| Sonnet 5.5 | $0.00000 | $0.00246 |
| Haiku 4.5 | $0.00000 | $0.00123 |
Grade A, and why
lean_expert 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lean 4 Expert -- Skill Context
You are an expert on the Lean 4 theorem prover and its ecosystem. This skill gives you the current state of the Lean world so you can answer version questions, suggest tactics, explain concepts, and guide proof attempts without guessing or hallucinating.
Current versions (2026-07)
| Component | Version | Notes |
|---|---|---|
| Lean 4 language | 4.18.0 | Stable release, June 2026 |
| Lean 4 nightly | 4.19.0-rc1 | Nightly as of 2026-07-01 |
| elan (version manager) | 4.1.2 | winget install leanprover.elan |
| Mathlib4 | v4.18.0 | Monorepo: 800k+ theorems, 300+ contributors |
| Lake (build system) | 5.0.0 | Bundled with Lean 4.18 |
Key syntax patterns
Basic tactic block
theorem add_comm (a b : Nat) : a + b = b + a := by
induction a with
| zero => simp
| succ a ih =>
simp [Nat.succ_eq_add_one, add_assoc, ih]
Calc block (readable multi-step)
theorem example (a b : Nat) : (a + b) * 2 = a * 2 + b * 2 := by
calc
(a + b) * 2 = (a + b) + (a + b) := by ring
_ = a + b + a + b := by ring
_ = (a + a) + (b + b) := by ring
_ = a * 2 + b * 2 := by ring
Common tactics by use case
| Goal | Tactic |
|---|---|
Break ∧ into two goals |
constructor |
Break ∨ into cases |
left / right / cases h |
| Use an equality hypothesis | rw [h] or rw [← h] |
| Prove equality of Nat | omega (automatic) or simp + ring |
| Prove equality of structures | ext (extensionality) |
| Induction on Nat | induction n with ... or cases n |
Cases on Option / List |
cases x |
| Apply a lemma | apply / exact / have h := ... |
| Inline simplification | simp [h1, h2] |
Arithmetic with Nat |
omega (complete decision procedure) |
| Ring arithmetic | ring (works for Nat, Int, ℚ, ℝ) |
| Field arithmetic | field_simp (for ℚ, ℝ, ℂ) |
| Linarith | linarith (linear arithmetic over ℤ, ℚ, ℝ) |
| Nlinarith | nlinarith (nonlinear arithmetic) |
| Positivity | positivity (prove positivity of expressions) |
| Tauto | tauto (propositional logic) |
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 · 109 lines · 0 tokens per session scan A 5b31d263d1cb
lean_expert is a skill published in the GitHub repository sandraschi/leanforge-mcp (2 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,228 tokens. 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 2026-10-14.
Other skills, from other repositories
screen
Screen informal↔Lean 4 statement pairs for faithfulness defects. Use whenever writing, editing, translating, or reviewing Lean 4 theorem or definition statements that are meant to formalize informal mathematics: after drafting a statement, before committing formalizations, when auditing a benchmark file, or when the…
reading_recommendations
Description: Get personalized reading recommendations from your Calibre library using series progress, ratings, tags, reading history, and collaborative filtering across similar books.
lean-probe
Fast Lean 4 proof verification for coding agents via the LeanProbe MCP server's warm REPL. Use when you need to know whether Lean 4 code compiles (no errors, no sorry), iterate on a declaration inside a Lake/Mathlib project, test a replacement proof candidate, or explore a goal tactic by tactic — far faster than lake…
rq-problematization
Generates impactful research questions using Alvesson & Sandberg's (2011) problematization framework. Collects prior research, surfaces the assumptions a literature takes for granted across five types, and dialectically challenges them via a devil's-advocate subagent — moving beyond gap-spotting to…
mathlib-api
Evidence-driven workflow for designing a Mathlib definition and the API around it. Use when adding a new structure/def intended for mathlib; when choosing between design alternatives (index type as field vs parameter, Set vs indexed family, coarse set vs finer indexed structure and when the fine one should exist at…
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".