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/pre-submitgit 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 | $0.00008 | $0.07945 |
| Opus 5 | $0.00004 | $0.03973 |
| Sonnet 5 | $0.00002 | $0.01589 |
| Haiku 4.5 | $0.00001 | $0.00795 |
Grade A, and why
pre-submit 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 — 737 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pre-submit - Pre-PR Submission Checklist
Final verification before submitting a PR to mathlib.
Usage
/pre-submit [file_path or directory]
/pre-submit --reset-intake (re-ask the Step 0a chain questions and rewrite the session file)
On Tau Ceti, use
/tauprinstead. It is the same discipline specialised to that repo's actual mechanics —tauceti-reviewon your own subscription, contests in the rubric thread,--force-with-leasepushes, target markers and author claims, scoreboard polling./pre-submitstays the generic checklist for mathlib and everything else.
Checklist
0. Scope and Provenance (roadmap projects)
- Chain intake answered once and persisted — not re-asked per PR
- Roadmap-named sources checked before the code was written; ported not rederived
- Open PRs checked for duplication — before writing, and again before creating
- No declaration claims mathlib-absence on a search-only basis (untruncated full-name
grep and a compiled
exampleprobe)
1. Compilation
-
lake buildsucceeds without errors - No warnings in modified files
- All
sorryremoved - No
#check,#print,#evaldebugging statements
2. File Quality
For each modified file:
- File length ≤ 1500 lines
- All lines ≤ 100 characters
- Proper copyright header
- Module docstring present
- Imports organized and minimal
3. Code Quality
- No bare
simp(usesimp only) - No
set_option maxHeartbeats(a proof that needs one is slow — run/buzzto diagnose and fix it; never raise the limit) - No
set_option trace.* - No
set_option pp.* - Instance names are explicit
- Naming follows conventions
4. Documentation
- All public definitions have docstrings
- All public theorems have docstrings (if non-obvious)
- Docstrings are informative and accurate
5. Linter Compliance
- No linter errors
- Any
@[nolint]is justified
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 · 737 lines · 8 tokens per session scan A 73d24fca1bd9
pre-submit is a command published in the GitHub repository CBirkbeck/mathlib-quality (32 stars, last pushed 13d ago), licensed MIT. It adds 8 tokens to every session and 7,945 once invoked, about $0.0000 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.