Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/CBirkbeck/mathlib-qualitynpx agentmods add commands/cbirkbeck/mathlib-quality/blueprintWrote 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/blueprint)<a href="https://agentmods.dev/commands/cbirkbeck/mathlib-quality/blueprint"><img src="https://agentmods.dev/badge/commands/cbirkbeck/mathlib-quality/blueprint/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/blueprint"><img src="https://agentmods.dev/badge/commands/cbirkbeck/mathlib-quality/blueprint.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 | $0.00241 | $0.11815 |
| Opus 5.5 | $0.00096 | $0.04726 |
| Sonnet 5.5 | $0.00048 | $0.02363 |
| Haiku 4.5 | $0.00024 | $0.01182 |
Grade A, and why
blueprint 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 — 1,119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/blueprint — Unformalise a Lean project into a Verso blueprint
Produce or update a project's blueprint: a Verso document where every public
declaration appears as a :::definition / :::theorem / :::lemma / :::proposition
/ :::corollary block with:
- the mathematical statement (not the Lean type) in standard mathematical prose with KaTeX math,
(lean := "Qualified.Lean.Name")linking the prose statement to one or more Lean declarations,{uses "label"}[]directives capturing dependency-graph edges,- a
:::proof "label"block holding a paragraph-level mathematical sketch — not a Lean tactic transcript — with its own{uses}cross-links.
Verso auto-computes the completion status (sorry-free vs. in-progress) from the
referenced Lean declarations' state. There is no \leanok directive in Verso; the
graph colour comes from the declaration state directly, so the blueprint and the
formal side cannot drift out of sync.
The published Verso blueprints worth eyeballing for style:
verso-sphere-packing,
verso-flt,
verso-carleson,
verso-noperthedron,
verso-algebraic-combinatorics.
This skill does NOT bootstrap a verso-blueprint repo from scratch — it expects the
project_template has been copied into the project (see Phase 0). It does NOT build
the HTML site — that's ./scripts/ci-pages.sh, also Phase 0 / Phase 6 territory. It
does the hard part: producing high-quality, mathematically faithful unformalisations.
Usage
/blueprint # whole project (default)
/blueprint <file.lean> # only this file's declarations
/blueprint --decl <Foo.bar> # ★ only this declaration + its dependency closure
/blueprint --update # re-sync: add stubs for new decls, flag stale `(lean := …)`
/blueprint --check # author nothing; just enumerate inventory and report drift
/blueprint --migrate-from-latex [<dir>] # convert an old leanblueprint LaTeX tree (default: blueprint/src/)
# into Verso chapter files (mechanical 1:1)
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 · 1,119 lines · 241 tokens per session scan A 11869233ee40
blueprint is a command published in the GitHub repository CBirkbeck/mathlib-quality (35 stars, last pushed 5d ago), licensed MIT. It adds 241 tokens to every session and 11,815 once invoked, about $0.0010 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.