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/CBirkbeck/mathlib-qualityWrote 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/cbirkbeck/mathlib-quality/overview)<a href="https://agentmods.dev/commands/cbirkbeck/mathlib-quality/overview"><img src="https://agentmods.dev/badge/commands/cbirkbeck/mathlib-quality/overview/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/commands/cbirkbeck/mathlib-quality/overview"><img src="https://agentmods.dev/badge/commands/cbirkbeck/mathlib-quality/overview.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 | $0.00009 | $0.07976 |
| Opus 5.5 | $0.00004 | $0.03190 |
| Sonnet 5.5 | $0.00002 | $0.01595 |
| Haiku 4.5 | $0.00001 | $0.00798 |
Grade A, and why
overview 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 1mo 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 — 712 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/overview - Deep Project Review
A slow, methodical review of the entire project. Produces a comprehensive inventory of every declaration, then performs deep analysis to find: moral duplications, generalization opportunities, missing API, and junk. This is not a quick scan. Take all the time needed. Do not skip steps.
Usage
/overview [directory_or_file] # full overview INCLUDING Step 9 mathlibable assessment
# (slow — full /mathlibable per public decl; plan on hours)
/overview [directory_or_file] --skip-mathlibable # everything except Step 9; faster draft view
Output: writes PROJECT_OVERVIEW.md in the project root. Per-decl mathlibable
detail reports go to .mathlib-quality/overview/mathlibable/<decl>.md.
Step 9 is the slowest by far. It dispatches one /mathlibable Agent per
non-skipped public declaration; each Agent runs the full 10-phase workflow
with the exhaustive nine-channel literature search. The orchestrator
narrates a one-line scoreboard between dispatches so you can leave the
session running. Use --skip-mathlibable when you want a fast structural
overview without the deep contribution assessment.
Philosophy
This command serves the same role as a senior mathematician reviewing a paper before submission:
- Are the definitions at the right level of generality?
- Are there lemmas that are morally the same and should be unified?
- Is there missing API that would make proofs cleaner?
- Are there definitions that shouldn't exist (duplicating mathlib or too specific)?
- Could results be stated more generally (rings instead of fields, etc.)?
Take your time. Read proofs carefully. Think about the mathematics, not just the syntax.
Phase 1: Inventory (Per-File Workers)
Step 1: Find Files
Find all .lean files (excluding .lake/, build/):
find . -name "*.lean" -not -path "./.lake/*" -not -path "./build/*" | sort
Step 2: Dispatch Per-File Inventory Agents
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.
- 1mo ago First seen · 712 lines · 9 tokens per session scan A 55b31b886b40
overview is a command published in the GitHub repository CBirkbeck/mathlib-quality (35 stars, last pushed 5d ago), licensed MIT. It adds 9 tokens to every session and 7,976 once invoked, about $0.0000 per session on Opus 5.5. 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
verify-math
Verify a self-authored mathematical result end to end by routing claims across adversarial review, numerical falsification, symbolic or CAS checks, and Lean, then aggregating one report. Use when a theorem, proposition, conjecture, or paper-wide mathematical argument needs the appropriate combination of verification…
diff
Quantitative volume comparison between a CadQuery model and a reference STEP file.
simulation-calibrator
Test and refine simulation accuracy with validation loops, bias detection, and continuous improvement frameworks.
arg-diagram
ARG academic-paper diagram mode — standalone structural & conceptual diagram generation.
plot
Publication Polish. Runs after results-analysis (Phase 7). Audits all tables and figures produced in Phases 4–7, upgrades them to top-journal standards by calling the table and figure skills.
graphite-morphology-classify
Classify graphite in a cast-iron micrograph per ASTM A247 / ISO 945-1, quantify nodularity, and read the matrix — the single most diagnostic observation in a cast-iron case.