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
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/benchflow-ai/skillsbench/lean4-memories)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/lean4-memories"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/lean4-memories/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-memories"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/lean4-memories.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 | $0.00045 | $0.02974 |
| Opus 5 | $0.00023 | $0.01487 |
| Sonnet 5 | $0.00009 | $0.00595 |
| Haiku 4.5 | $0.00005 | $0.00297 |
Grade A, and why
lean4-memories 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 9d 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-memories — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lean 4 Memories
Overview
This skill enables persistent learning and knowledge accumulation across Lean 4 formalization sessions by leveraging MCP (Model Context Protocol) memory servers. It transforms stateless proof assistance into a learning system that remembers successful patterns, avoids known dead-ends, and adapts to project-specific conventions.
Core principle: Learn from each proof session and apply accumulated knowledge to accelerate future work.
When to Use This Skill
This skill applies when working on Lean 4 formalization projects, especially:
- Multi-session projects - Long-running formalizations spanning days/weeks/months
- Repeated proof patterns - Similar theorems requiring similar approaches
- Complex proofs - Theorems with multiple attempted approaches
- Team projects - Shared knowledge across multiple developers
- Learning workflows - Building up domain-specific proof expertise
Especially important when:
- Starting a new session on an existing project
- Encountering a proof pattern similar to previous work
- Trying an approach that previously failed
- Needing to recall project-specific conventions
- Building on successful proof strategies from earlier sessions
How Memory Integration Works
Memory Scoping
All memories are scoped by:
- Project path - Prevents cross-project contamination
- Skill context - Memories tagged with
lean4-memories - Entity type - Structured by pattern type (ProofPattern, FailedApproach, etc.)
Example scoping:
Project: /Users/freer/work/exch-repos/exchangeability-cursor
Skill: lean4-memories
Entity: ProofPattern:condExp_unique_pattern
Memory Types
1. ProofPattern - Successful proof strategies
Store when: Proof completes successfully after exploration
Retrieve when: Similar goal pattern detected
2. FailedApproach - Known dead-ends to avoid
Store when: Approach attempted but failed/looped/errored
Retrieve when: About to try similar approach
What ships with it
2 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.
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.
- 9d ago First seen · 444 lines · 45 tokens per session scan A 158e14b3e8a1
lean4-memories is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,974 once invoked, about $0.0002 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
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
ax-cpp-agent-memory-skills
Use when writing C++ code with axllm for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.
ax-cpp-agent-context
Use when writing C++ code with axllm for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
wax
Swift framework guidance for Wax on-device memory/RAG. Use when writing Swift code with the public Memory facade, experimental PhotoMemory / VideoMemory, BuiltInMultimodalEmbeddings, embedding providers, retrieval modes, or hybrid search. For agent operators using the Wax MCP server tools, use the separate wax-mcp…
codspeed-optimize
Autonomously optimize code for performance using CodSpeed benchmarks, flamegraph analysis, and iterative improvement. Use this skill whenever the user wants to make code faster, reduce CPU usage, optimize memory, improve throughput, find performance bottlenecks, or asks to 'optimize', 'speed up', 'make faster'…