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 commands/frenzymath/archon/refactorgit clone --depth 1 https://github.com/frenzymath/ArchonWhat 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 | $0.00014 | $0.01188 |
| Opus 5 | $0.00007 | $0.00594 |
| Sonnet 5 | $0.00003 | $0.00238 |
| Haiku 4.5 | $0.00001 | $0.00119 |
Grade A, and why
refactor 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.
This is a copy
98% identical to refactor — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lean4 Refactor
Strategy-level proof simplification: find better proof approaches, leverage mathlib, and extract reusable helpers. Complements /lean4:golf (tactic-level optimization) and /lean4:review (read-only audit).
Mutating command: Edits files with user approval. Does not change theorem statements, introduce axioms, or create commits.
Usage
/lean4:refactor File.lean # Refactor all proofs in file
/lean4:refactor File.lean:149 # Refactor proof at line 149
/lean4:refactor --scope=changed # Refactor files modified since last commit
/lean4:refactor --scope=changed --dry-run # Report opportunities without editing
Inputs
| Arg | Required | Description |
|---|---|---|
| target | No | File or File.lean:line |
| --scope | No | file (default with target), changed (default without target) |
| --dry-run | No | Report only, do not edit |
| --search | No | quick (default) or full (exhaustive mathlib search) |
| --extract-helpers | No | on (default) or off (skip helper extraction) |
Scope Behavior
| Input | Scope |
|---|---|
File.lean |
All proofs in file |
File.lean:149 |
Single proof containing line 149 |
| No target | --scope=changed (files modified since last commit) |
--scope=changed |
Files modified since last commit |
Line target: Identifies the enclosing theorem/lemma/def containing the given line and refactors that proof only.
Large-run confirmation: When --scope=changed touches >5 files or >20 opportunities, confirm before proceeding.
Preconditions
- Target proofs must compile (no sorries, no build errors in scope)
- Run
/lean4:proveor/lean4:autoprovefirst if there are open sorries
Refusal: If preconditions are not met:
⚠️ Cannot refactor: File.lean has 2 sorries and 1 build error.
Run /lean4:prove first, then retry /lean4:refactor.
Actions
- Audit — Read target proofs, identify repeated patterns, long proofs (>30 lines), hand-rolled arguments, case splits replaceable by
congr/EqOn/EventuallyEq, thin definition APIs - Search — For each opportunity, search mathlib via LSP-first protocol.
--search=quick: up to 2 LSP queries per opportunity.--search=full: up to 5 queries with module exploration. - Plan — Present findings with estimated impact:
## Refactor Plan — File.lean ### Strategy Improvements 1. [proof] (line N): [current] → Use [mathlib lemma] (saves ~N lines) ### Helper Extraction 1. [pattern] — Nx (lines ...) → Extract `helper_name` ### Estimated Impact - Lines before: N → after: ~N | Helpers: N | New mathlib lemmas: N - Approval — Ask before each batch (
--dry-runstops here). A batch groups opportunities within a single proof or closely related proofs. Prompt:Apply batch N (M changes)? [yes / skip / stop]— yes applies, skip moves to next batch, stop ends the session. - Apply — Edit files, verify with
lean_diagnostic_messagesafter each batch; revert batch on any new diagnostic or sorry increase - Verify —
lake env lean <file>file gate (run from project root);lake buildproject gate if multi-file. If final gate fails, revert all batches applied in this session. - Report — Summarize changes applied, helpers extracted, line count delta
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 · 96 lines · 14 tokens per session scan A c18061f79915
refactor is a command published in the GitHub repository frenzymath/Archon (213 stars, last pushed 16d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,188 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to refactor, differing in 1 line, and is treated as a copy.
Other commands, from other repositories
wisp-dashboard
Open the WISP dashboard in your browser.
forkmind
Start ForkMind or branch/inspect/regression-test an LLM call.
graph-open
The web UI requires the human-only full-authority token (uitoken). It is stored in no file, so you cannot know it and must not try to find it.
graph-new
Decompose a natural-language requirement into an execution graph and register it (does not run it).
graph-lock
Guide the user through locking/unlocking a graph (only a human can do it).
graph-run
Start a run and pump the cursor to the end.