SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
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 benchflow-ai/skillsbench --skill lean4-theorem-provinggit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote 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/benchflow-ai/skillsbench/lean4-theorem-proving)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/lean4-theorem-proving"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/lean4-theorem-proving/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/benchflow-ai/skillsbench/lean4-theorem-proving"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/lean4-theorem-proving.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00068 | $0.02144 |
| Opus 5 | $0.00034 | $0.01072 |
| Sonnet 5 | $0.00014 | $0.00429 |
| Haiku 4.5 | $0.00007 | $0.00214 |
Grade A, and why
lean4-theorem-proving 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- lean4-theorem-proving — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lean 4 Theorem Proving
Core Principle
Build incrementally, structure before solving, trust the type checker. Lean's type checker is your test suite.
Success = lake build passes + zero sorries + zero custom axioms. Theorems with sorries/axioms are scaffolding, not results.
Quick Reference
| Resource | What You Get | Where to Find |
|---|---|---|
| Interactive Commands | 10 slash commands for search, analysis, optimization, repair | Type /lean in Claude Code (full guide) |
| Automation Scripts | 19 tools for search, verification, refactoring, repair | Plugin scripts/ directory (scripts/README.md) |
| Subagents | 4 specialized agents for batch tasks (optional) | subagent-workflows.md |
| LSP Server | 30x faster feedback with instant proof state (optional) | lean-lsp-server.md |
| Reference Files | 18 detailed guides (phrasebook, tactics, patterns, errors, repair, performance) | List below |
When to Use
Use for ANY Lean 4 development: pure/applied math, program verification, mathlib contributions.
Critical for: Type class synthesis errors, sorry/axiom management, mathlib search, measure theory/probability work.
Tools & Workflows
7 slash commands for search, analysis, and optimization - type /lean in Claude Code. See COMMANDS.md for full guide with examples and workflows.
16 automation scripts for search, verification, and refactoring. See scripts/README.md for complete documentation.
Lean LSP Server (optional) provides 30x faster feedback with instant proof state and parallel tactic testing. See lean-lsp-server.md for setup and workflows.
Subagent delegation (optional, Claude Code users) enables batch automation. See subagent-workflows.md for patterns.
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/axiom-elimination.md 5.9 KB
- references/calc-patterns.md 8.7 KB
- references/compilation-errors.md 20 KB
- references/compiler-guided-repair.md 18 KB
- references/domain-patterns.md 25 KB
- references/instance-pollution.md 16 KB
- references/lean-lsp-server.md 8.9 KB
- references/lean-lsp-tools-api.md 25 KB
- references/lean-phrasebook.md 17 KB
- references/mathlib-guide.md 14 KB
- references/mathlib-style.md 8.5 KB
- references/measure-theory.md 27 KB
- references/performance-optimization.md 16 KB
- references/proof-golfing-patterns.md 11 KB
- references/proof-golfing-safety.md 5.8 KB
- references/proof-golfing.md 3.6 KB
- references/proof-refactoring.md 28 KB
- references/sorry-filling.md 4.8 KB
- references/subagent-workflows.md 18 KB
- references/tactics-reference.md 16 KB
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.
- 8d ago First seen · 156 lines · 68 tokens per session scan A ccdf91ca8b6e
lean4-theorem-proving is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 2,144 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
content-creator-setup
One-time onboarding for the content creator workflow — content pipeline stages, trend expiration, cross-platform cascades, heavy idea parking. After successful setup this skill is excluded from selection until the marker file is deleted.
habit-formation
Atomic habits, cue-routine-reward loops, habit stacking, accountability systems, and behavior change.
aiwg-help
Display all available AIWG CLI commands, their arguments, and usage examples.
trading-manual-writer
A writing skill for creating sections of a trading manual for beginners and individual investors. It explains financial instruments or trading topics in Markdown and can include SVG illustrations.
beam-concepts
Explains core Apache Beam programming model concepts including PCollections, PTransforms, Pipelines, and Runners. Use when learning Beam fundamentals or explaining pipeline concepts.