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/cbirkbeck/mathlib-quality/split-filegit clone --depth 1 https://github.com/CBirkbeck/mathlib-qualityWhat 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 | $0.01658 |
| Opus 5 | $0.00007 | $0.00829 |
| Sonnet 5 | $0.00003 | $0.00332 |
| Haiku 4.5 | $0.00001 | $0.00166 |
Grade A, and why
split-file 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/split-file - Split Large Lean Files
Split a large Lean file (>1500 lines) into smaller, focused modules.
Usage
/split-file [file_path]
Splitting Strategy
Step 1: Analyze the File
- Get the file outline using
lean_file_outline - List all declarations with their line numbers
- Group declarations by naming prefix (e.g.,
cauchyPrincipalValue*,residue*)
Step 2: Identify Natural Groupings
Group declarations by the object they work on, identified by naming patterns:
| Prefix Pattern | Suggested File |
|---|---|
cauchyPrincipalValue* |
CauchyPrincipalValue.lean |
residue*, Residue* |
Residue.lean |
pv_*, PV* |
PrincipalValue.lean |
winding*, Winding* |
WindingNumber.lean |
integral_* |
Integration.lean |
| Core definitions | Basic.lean or Defs.lean |
Step 3: Determine Split Structure
Option A: Two-file split (for 1500-3000 lines)
Module/
├── Basic.lean -- Core definitions + simple lemmas
└── Theorems.lean -- Main results (imports Basic)
Option B: Multi-file split (for >3000 lines)
Module/
├── Defs.lean -- Core definitions only
├── Basic.lean -- API lemmas (imports Defs)
├── Topic1.lean -- Grouped lemmas (imports Basic)
├── Topic2.lean -- Grouped lemmas (imports Basic)
└── Main.lean -- Main theorems (imports all above)
Step 4: Execute the Split
For each new file:
- Create the file with proper header:
/-
Copyright (c) 2024 [Author]. All rights reserved.
Released under Apache 2.0 license as described in the file LICENSE.
Authors: [Author]
-/
import [necessary imports]
/-!
# [Module Title]
[Brief description]
## Main definitions/results
* `foo`: Description
-/
-
Move declarations preserving order (dependencies must come before dependents)
-
Update imports in all affected files
-
Verify each file compiles before proceeding to next
Step 5: Verify
- Run
lake buildon each new file - Ensure no circular imports
- Check that downstream files still compile
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 · 213 lines · 14 tokens per session scan A 95da4978f7a1
split-file is a command published in the GitHub repository CBirkbeck/mathlib-quality (32 stars, last pushed 13d ago), licensed MIT. It adds 14 tokens to every session and 1,658 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.