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/gyf9712/stat-theory-skillsnpx agentmods add skills/gyf9712/stat-theory-skills/proof-repairWrote 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/skills/gyf9712/stat-theory-skills/proof-repair)<a href="https://agentmods.dev/skills/gyf9712/stat-theory-skills/proof-repair"><img src="https://agentmods.dev/badge/skills/gyf9712/stat-theory-skills/proof-repair/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/skills/gyf9712/stat-theory-skills/proof-repair"><img src="https://agentmods.dev/badge/skills/gyf9712/stat-theory-skills/proof-repair.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 | $0.00114 | $0.09404 |
| Opus 5 | $0.00057 | $0.04702 |
| Sonnet 5 | $0.00023 | $0.01881 |
| Haiku 4.5 | $0.00011 | $0.00940 |
Grade A, and why
proof-repair 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 12d 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 — 718 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proof-Repair — Literature-Backed Repair Plans for Mathematical Proofs
🔬 Model Recommendation: Run this skill on Claude Opus for best results. Repair design + literature verification requires deep reasoning. If your session is not on Opus, run
/model opusbefore invoking. Heavy reasoning (literature search, verification, full proof writing) will use Opus sub-agents.
Takes a /proofcheck audit (or a raw .tex file with known issues) and produces
self-consistent repair plans with new literature references for every fixable issue.
Pipeline position:
/proofcheck → [THIS SKILL] → /proof-writer
Find issues Fix + literature Write complete proofs
Upstream: /proofcheck (produces audit/ with provability triage + blockage reports)
This skill: audit/ → REPAIR_PLAN.md + patched .bib + per-unit repair files
Downstream: /proof-writer (writes complete corrected proofs for each repair)
Register for any proof text this skill writes. Full-proof creation delegates to
/proof-writer, which carries the register. But LaTeX patches this skill writes
directly (Fill-Skipped-Steps, Insert-Lemma, inserted derivations) must follow the same
Big Four register: key steps on display lines, connectives naming the logical move
(displays carry the what, connectives the why), no walls of undisplayed algebra, no
Step 1 / Step 2 bulletization. Single source of truth: the "Mathematical Register and
Readability (Big Four)" section of ../stat-shared-references/stat-theory-writing.md. A
repair must not fix correctness while regressing readability.
Context: $ARGUMENTS
0. Locate Inputs
Parse $ARGUMENTS to find the paper workspace.
Expected structure (created by /proofcheck):
papers/<paper-name>/
paper.tex
CHECK_PLAN.md
EXECUTION_ORDER.md
audit/
01_index/theorem_inventory.md
02_ledgers/{notation,assumption,constants}_ledger.md
03_dependencies/dependency_graph.md
04_local_checks/section_*/*_check.md
05_adversarial/{hidden_assumptions,counterexamples}.md
06_reports/{issue_log.md, FINAL_REPORT.md}
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.
- 12d ago First seen · 718 lines · 114 tokens per session scan A 22fe04dd3206
proof-repair is a skill published in the GitHub repository gyf9712/stat-theory-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 9,404 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
did
Design, estimate, validate, and write up a difference-in-differences analysis, using the post-2018 heterogeneity-robust toolkit with an explicit statement of which parallel-trends assumption is imposed. TRIGGER on "difference-in-differences", "DiD", "TWFE", "event study", "staggered adoption", "parallel trends"…
iv
Design, estimate, validate, and write up an instrumental-variables analysis: single-instrument LATE designs, weak-instrument-robust inference, shift-share instruments, formula instruments that need recentering, and leniency (judge and examiner) designs estimated by UJIVE. TRIGGER on "instrumental variable", "IV"…
conjoint
Design, analyze, and write up conjoint experiments in both traditions: as randomized experiments identifying average marginal component effects, and as preference-measurement instruments (hierarchical Bayes partworths, WTP, choice-share simulation), with measurement-error correction, multiple-testing correction, and a…
research-talk
Author a Quarto reveal.js deck for a research talk: seminar, conference, job talk, brown bag. TRIGGER on "slides for my talk", "seminar deck", "job talk", "turn this paper into slides", "add an appendix slide", "export a handout". Classroom material is teaching-lecture; auditing an existing deck is slide-review.
field-experiment
Design, analyze, and write up randomized experiments (field experiments, A/B tests, RCTs): stratified and clustered designs, randomization inference, covariate adjustment done right, noncompliance, attrition and gated outcomes, treatment-effect heterogeneity, and interference. TRIGGER on "A/B test", "randomized…
preregister
Draft a registry-ready preregistration or preanalysis plan for AsPredicted, OSF, or the AEA RCT Registry. TRIGGER on "preregister", "draft a preregistration", "AsPredicted form", "OSF prereg", "AEA RCT registry", "PAP", "preanalysis plan", or before launching a vignette, conjoint, MTurk/Prolific, or field experiment.…