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 agentmods add skills/nasqret/lean-interact/lean-sessionnpx skills add nasqret/lean-interact --skill lean-sessiongit clone --depth 1 https://github.com/nasqret/lean-interactWhat 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 | $0.00154 | $0.01538 |
| Opus 5 | $0.00077 | $0.00769 |
| Sonnet 5 | $0.00031 | $0.00308 |
| Haiku 4.5 | $0.00015 | $0.00154 |
Grade A, and why
lean-session 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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lean-session
Brings up the three live views and proves that each one is actually alive. Repository root:
/path/to/lean-interact.
The user asked for all three views explicitly. They are not redundant; each answers a different question:
| View | Answers | Where |
|---|---|---|
Terminal watcher, tools/live.py |
did the last save compile, and how fast | tmux pane |
| VS Code infoview, Lean 4 extension | what is the goal state right here | VS Code |
Browser dashboard, tools/dashboard.py |
where do we stand overall | browser tab |
All three read the same contract: .live/status.json, schema 1.
Start
tools/session.sh --help # read this FIRST: it is authoritative on panes, flags, port
tools/session.sh # start everything
tools/session.sh starts the watcher, starts the dashboard, and opens
Scratch/Current.lean in VS Code. macOS does not put the code CLI on PATH by default; the
script uses /Applications/Visual Studio Code.app/Contents/Resources/app/bin/code.
Take the tmux session name and the dashboard port from the script's --help or from its
startup output. Do not assume a port number - report the one the script actually printed.
Confirm it is alive - all three checks, every time
Do not report "session started" on the strength of the launcher exiting 0.
1. The watcher is drawing. Touch the live file and confirm the status file moves:
touch Scratch/Current.lean
sleep 3
jq '{state, finished_at, elapsed_s, counts}' .live/status.json
finished_at must be within the last few seconds. If it is not, the watcher is not
polling - see Troubleshooting.
2. The dashboard port is listening.
tmux ls # the session exists
lsof -nP -iTCP:<port> -sTCP:LISTEN # something is bound to the port
Then tell the user the exact URL, http://127.0.0.1:<port>/, so it can be clicked.
3. VS Code has the file open with the Lean 4 extension active. The infoview appears once the cursor is inside a proof. If the extension is still loading Mathlib's oleans, the infoview says so; that is normal on the first open and takes a minute.
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.
- 2d ago First seen · 135 lines · 154 tokens per session scan A bc757b0c58a6
lean-session is a skill published in the GitHub repository nasqret/lean-interact (10 stars, last pushed 24d ago), licensed MIT. It adds 154 tokens to every session and 1,538 once invoked, about $0.0008 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 2026-08-31.
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…
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…
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…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.