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/cameronfreer/lean4-skillsWrote 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/commands/cameronfreer/lean4-skills/share-insight)<a href="https://agentmods.dev/commands/cameronfreer/lean4-skills/share-insight"><img src="https://agentmods.dev/badge/commands/cameronfreer/lean4-skills/share-insight.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.01087 |
| Opus 5 | $0.00009 | $0.00544 |
| Sonnet 5 | $0.00003 | $0.00217 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade A, and why
share-insight 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Share Insight
Draft and submit a reusable insight (pattern, antipattern, or mixed) as a
GitHub issue on cameronfreer/lean4-skills.
Precondition
Invoke this command only if the user explicitly ran it or explicitly agreed to draft a shareable insight. If invoked without prior opt-in, ask:
That seems reusable beyond this task. Want me to draft a shareable insight?
If the user explicitly ran /lean4-contribute:share-insight, treat that as opt-in.
Do not proceed unless the user confirms. Do not mine git diff, infer insight
candidates, or ask structured questions until consent is given.
Discovering Candidates
Once the user has opted in (see Precondition above), look at:
- Current conversation / session context
- Current git diff (
git diffandgit diff --cached) - Recently touched
.leanfiles
From these, infer 1–5 candidate insights. For each candidate, note:
- A one-line title (keep titles generic — avoid project-specific names, paths, or identifiers)
- Classification: pattern (what worked), antipattern (what failed), or mixed (worked in some contexts, failed in others)
Present the candidates as a numbered list and ask the user to pick one (or describe a different insight). Proceed with the selected insight.
Gathering Context
For the chosen insight, collect or infer:
- Kind — pattern / antipattern / mixed
- Title — Concise, descriptive title
- Context — What were you working on when you discovered this?
- Symptom / trigger — What behavior or error led to the discovery?
- What worked / what failed — The core lesson
- Why it matters — Impact on proving, performance, readability, or correctness
- Minimal example — Smallest Lean snippet illustrating the insight (strip project-specific details)
- When to use / when not to — Applicability boundaries
- Confidence — High / medium / low — how sure are you this generalizes?
- Privacy / redaction check — Scan for filesystem paths, usernames, API keys, or other sensitive data and redact them. Flag anything you redacted so the user can verify.
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 · 130 lines · 17 tokens per session scan A 285db1dedb58
share-insight is a command published in the GitHub repository cameronfreer/lean4-skills (432 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,087 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
handoff
Export a Waybill Bundle by default, or import one when requested.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.