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 skills add cxcscmu/SkillLearnBench --skill california-small-claimsgit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote 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/cxcscmu/skilllearnbench/california-small-claims)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/california-small-claims"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/california-small-claims/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/cxcscmu/skilllearnbench/california-small-claims"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/california-small-claims.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 | $0.00030 | $0.01339 |
| Opus 5 | $0.00015 | $0.00669 |
| Sonnet 5 | $0.00006 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
california-small-claims 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 7d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
California Small Claims Court SC-100 Form
Overview
The SC-100 form ("Plaintiff's Claim and Order to Go to Small Claims Court") is a 6-page fillable PDF. Pages 1, 5, and 6 are informational; data entry is on pages 2–4.
Field Sections by Page
Page 2 – Plaintiff & Defendant Info + Claim Amount
Plaintiff (Section 1)
| Field ID suffix | Description |
|---|---|
PxCaption[0].Plaintiff[0] |
Plaintiff name(s) header |
PlaintiffName1[0] |
Plaintiff full name |
PlaintiffPhone1[0] |
Plaintiff phone |
PlaintiffAddress1[0] |
Plaintiff street address |
PlaintiffCity1[0] |
Plaintiff city |
PlaintiffState1[0] |
Plaintiff state |
PlaintiffZip1[0] |
Plaintiff ZIP |
PlaintiffMailingAddress1[0] |
Mailing address (if different) |
EmailAdd1[0] |
Plaintiff email |
Checkbox1[0] |
More than two plaintiffs (check /1 if yes) |
Checkbox2[0] |
Fictitious name (check /1 if yes) |
Checkbox3[0] |
Licensee/payday lender (check /1 if yes) |
Defendant (Section 2)
| Field ID suffix | Description |
|---|---|
DefendantName1[0] |
Defendant full name |
DefendantPhone1[0] |
Defendant phone |
DefendantAddress1[0] |
Defendant street address |
DefendantCity1[0] |
Defendant city |
DefendantState1[0] |
Defendant state |
DefendantZip1[0] |
Defendant ZIP |
DefendantMailingAddress1[0] |
Defendant mailing (if different) |
Checkbox4[0] |
More than one defendant |
Checkbox5[0] |
Defendant on active military duty |
Claim (Section 3)
| Field ID suffix | Description |
|---|---|
PlaintiffClaimAmount1[0] |
Dollar amount claimed |
Lia[0].FillField2[0] |
3a: Why does defendant owe money |
Page 3 – When/How + Venue + Misc
| Field ID suffix | Description |
|---|---|
Lib[0].Date2[0] |
3b: Date started (if time period) |
Lib[0].Date3[0] |
3b: Through date (if time period) |
Lib[0].Date1[0] |
3b: Single date (if specific date) |
Lic[0].FillField1[0] |
3c: How amount was calculated |
Checkbox1[0] |
Need more space (attach MC-031) |
Item4[0].Checkbox50[0] |
Sec 4: Yes – asked defendant to pay |
Item4[0].Checkbox50[1] |
Sec 4: No – did not ask |
Item4[0].FillField2[0] |
Sec 4: Explanation if No |
Lia[0].Checkbox5cb[0] |
Sec 5a: Defendant lives/does business here |
Lib[0].Checkbox5cb[0] |
Sec 5b: Buyer/lessee signed contract here |
Lic[0].Checkbox5cb[0] |
Sec 5c: Retail installment contract |
Lid[0].Checkbox5cb[0] |
Sec 5d: Vehicle finance sale |
Lie[0].Checkbox5cb[0] |
Sec 5e: Other |
Lie[0].FillField55[0] |
Sec 5e: Other (specify) |
item6[0].ZipCode1[0] |
Sec 6: ZIP of venue |
item7[0].Checkbox60[0] |
Sec 7: Yes – attorney-client fee dispute |
item7[0].Checkbox60[1] |
Sec 7: No |
item8[0].Checkbox61[0] |
Sec 8: Yes – suing public entity |
item8[0].Checkbox61[1] |
Sec 8: No |
item8[0].Date4[0] |
Sec 8: Date claim filed with public entity |
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.
- 7d ago First seen · 97 lines · 30 tokens per session scan A 511399db7f6e
california-small-claims is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,339 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
pdf-editing
Complete guide for reading and editing PDF documents with PyMuPDF.
PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.
marker
Convert PDF documents to Markdown using markersingle. Use when Claude needs to extract text content from PDFs while preserving LaTeX formulas, equations, and document structure. Ideal for academic papers and technical documents containing mathematical notation.
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.