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/bump-mathlib)<a href="https://agentmods.dev/commands/cbirkbeck/mathlib-quality/bump-mathlib"><img src="https://agentmods.dev/badge/commands/cbirkbeck/mathlib-quality/bump-mathlib/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/bump-mathlib"><img src="https://agentmods.dev/badge/commands/cbirkbeck/mathlib-quality/bump-mathlib.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 | $0.00016 | $0.02939 |
| Opus 5.5 | $0.00006 | $0.01176 |
| Sonnet 5.5 | $0.00003 | $0.00588 |
| Haiku 4.5 | $0.00002 | $0.00294 |
Grade A, and why
bump-mathlib 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/bump-mathlib - Bump Mathlib and Fix Breakage
Update the mathlib dependency (or merge upstream for mathlib PRs), build, and fix all errors caused by the bump.
Usage
/bump-mathlib # Auto-detect context and bump to latest
/bump-mathlib <commit-or-date> # Bump to a specific mathlib version/date
Workflow
Step 1: Detect Context
Determine whether this is:
A) A standalone project using mathlib as a dependency
- Has
lakefile.leanorlakefile.tomlwith a mathlib dependency - Check for
require mathlibin lakefile
B) A mathlib PR (working directly in mathlib4)
- Check:
git remote -vshowsleanprover-community/mathlib4 - Or: current repo IS mathlib4
Report which context was detected before proceeding.
Step 2: Perform the Bump
Context A: Standalone Project
- Read the current lakefile (
lakefile.leanorlakefile.toml) - Find the current mathlib revision (look for
require mathlibwith arevor commit hash) - Update to the target version:
- If no target specified: update to latest mathlib
master - If target specified: use that commit/tag
- If no target specified: update to latest mathlib
- Run
lake update mathlibto update the lockfile
# Update lake-manifest.json
lake update mathlib
Context B: Mathlib PR
- Ensure upstream remote exists:
git remote -v | grep upstream || git remote add upstream https://github.com/leanprover-community/mathlib4.git - Fetch upstream:
git fetch upstream - Merge upstream master:
git merge upstream/master - If there are merge conflicts, resolve them:
- For files only modified in upstream: accept theirs
- For files modified in both: present conflicts to user for guidance
- For files only modified locally: keep ours
Step 3: Fetch Cached Artifacts (verification gate)
CRITICAL: Always fetch the Mathlib cache before building, otherwise compilation will take hours.
lake exe cache get
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 · 310 lines · 16 tokens per session scan A 3d87acd6229a
bump-mathlib is a command published in the GitHub repository CBirkbeck/mathlib-quality (35 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 2,939 once invoked, about $0.0001 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.