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 cat-xierluo/legal-skills --skill legal-skill-evaluationgit clone --depth 1 https://github.com/cat-xierluo/legal-skillsWrote 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/cat-xierluo/legal-skills/legal-skill-evaluation)<a href="https://agentmods.dev/skills/cat-xierluo/legal-skills/legal-skill-evaluation"><img src="https://agentmods.dev/badge/skills/cat-xierluo/legal-skills/legal-skill-evaluation/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/cat-xierluo/legal-skills/legal-skill-evaluation"><img src="https://agentmods.dev/badge/skills/cat-xierluo/legal-skills/legal-skill-evaluation.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 | $0.00096 | $0.04298 |
| Opus 5.5 | $0.00038 | $0.01719 |
| Sonnet 5.5 | $0.00019 | $0.00860 |
| Haiku 4.5 | $0.00010 | $0.00430 |
Grade A, and why
legal-skill-evaluation 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 14d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/capability-suite-false-verified.json 469 B
- assets/evaluation-package-false-pass.json 714 B
- assets/evaluation-package-historical-omission.json 438 B
- assets/evaluation-package-legal-near-miss.json 905 B
- assets/evaluation-package-missing-dimension.json 332 B
- assets/evaluation-package-out-of-scope-false-pass.json 1.0 KB
- assets/evaluation-package-scope-mismatch.json 406 B
- assets/evaluation-package-stale-candidate.json 388 B
- assets/evaluation-package-unbound-false-pass.json 998 B
- assets/evaluation-package-valid.json 183 B
- assets/semantic-attachment-limit-omission.md 146 B
- assets/semantic-objective-false-verdict.md 205 B
- CHANGELOG.md 57 KB
- config/capability-run-receipts.example.json 1.5 KB
- config/evaluation-package.example.json 9.6 KB
- config/instruction-stability-contract.json 7.8 KB
- evals/case-analysis-20260808/calibration-report.md 11 KB
- evals/case-analysis-20260808/capability-suite.json 6.2 KB
- evals/case-analysis-20260808/evaluation-package.json 11 KB
- evals/case-analysis-20260808/materials/familiar-sample.md 1.3 KB
- evals/case-analysis-20260808/materials/missing-context.md 629 B
- evals/case-analysis-20260808/materials/peer-unfamiliar.md 898 B
- evals/case-analysis-20260808/runs/familiar-sample-output.md 24 KB
- evals/case-analysis-20260808/runs/missing-context-output.md 3.4 KB
- evals/case-analysis-20260808/runs/peer-unfamiliar-output.md 3.2 KB
- evals/case-analysis-20260808/semantic-cases/anonymization-toggle.md 845 B
- evals/case-analysis-20260808/semantic-cases/fact-statement-distinction.md 554 B
- evals/case-analysis-20260808/semantic-cases/json/CASE-ANON-TOGGLE_input.json 286 B
- evals/case-analysis-20260808/semantic-cases/json/CASE-FACT-STMT_input.json 354 B
- evals/case-analysis-20260808/semantic-cases/json/CASE-NO-FABRICATE_input.json 365 B
- evals/case-analysis-20260808/semantic-cases/json/CASE-NO-RECALL-ARTICLE_input.json 284 B
- evals/case-analysis-20260808/semantic-cases/json/CASE-OBJ-MISSING_input.json 512 B
- evals/case-analysis-20260808/semantic-cases/no-fabricated-missing.md 486 B
- evals/case-analysis-20260808/semantic-cases/no-recalled-article-number.md 578 B
- evals/case-analysis-20260808/semantic-cases/objective-missing.md 663 B
- evals/case-analysis-bundle-PLAN.md 5.4 KB
- evals/case-bundle-260705/calibration-findings.md 15 KB
- evals/case-bundle-260705/case-analysis-case-01.md 23 KB
- evals/case-bundle-260705/trademark-case-01.md 23 KB
- evals/contract-calibration-260730/calibration-report.md 11 KB
- evals/contract-calibration-260730/capability-regression-seed.json 4.6 KB
- evals/contract-calibration-260730/capability-suite.json 38 KB
- evals/contract-calibration-260730/contract_copilot_micro_probe.py 12 KB runs code
- evals/contract-calibration-260730/current-run-receipts.json 43 KB
- evals/contract-calibration-260730/evaluation-package.json 13 KB
- evals/contract-calibration-260730/micro-runs/acceptance-payment-input.json 551 B
- evals/contract-calibration-260730/micro-runs/acceptance-payment-output.md 510 B
- evals/contract-calibration-260730/micro-runs/attachment-missing-gate-report.json 1.2 KB
- evals/contract-calibration-260730/micro-runs/attachment-missing-input.json 654 B
- evals/contract-calibration-260730/micro-runs/attachment-missing-output.md 730 B
- evals/contract-calibration-260730/micro-runs/change-fee-input.json 543 B
- evals/contract-calibration-260730/micro-runs/change-fee-output.md 534 B
- evals/contract-calibration-260730/micro-runs/contract-micro-producer-self-success-probe.json 964 B
- evals/contract-calibration-260730/micro-runs/contract-micro-report-field-collapse-probe.json 423 B
- evals/contract-calibration-260730/micro-runs/design-ip-use-input.json 545 B
- evals/contract-calibration-260730/micro-runs/design-ip-use-output.md 546 B
- evals/contract-calibration-260730/micro-runs/jurisdiction-input.json 490 B
- evals/contract-calibration-260730/micro-runs/jurisdiction-output.md 528 B
- evals/contract-calibration-260730/micro-runs/notice-input.json 532 B
- evals/contract-calibration-260730/micro-runs/notice-output.md 547 B
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.
- 14d ago Changed · +2 lines e838267f8a3f
- 21d ago Changed · +3 lines 7c1f184a84e7
- 1mo ago First seen · 254 lines · 96 tokens per session scan A a70285cbb281
legal-skill-evaluation is a skill published in the GitHub repository cat-xierluo/legal-skills (754 stars, last pushed today), with no licence file. It adds 96 tokens to every session and 4,298 once invoked, about $0.0004 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 2026-09-20.
Other skills, from other repositories
policy-creation
Guide for adding new enterprise policies to Chromium. Complete guide for policy definitions, pref mapping, and writing tests.
accessibility-testing
Test for WCAG 2.2 AA compliance with axe-core + Playwright, keyboard navigation audits, screen reader testing, ARIA pattern validation, and legal compliance mapping (ADA, EAA, Section 508). Automated tools catch 30-40% of issues — this skill covers automated and manual testing together. Use when: "accessibility,"…
compliance-testing
Test for regulatory compliance: GDPR/CMP consent verification, Google Consent Mode v2, Global Privacy Control (GPC), CCPA/US state opt-out, EU AI Act Article 50 transparency, Better Ads Standards, and cookie-inventory auditing. Covers automated consent-flow testing, policy-based script blocking before consent, and…
ring:adding-multi-tenancy
Adding database-per-tenant isolation into a Go service end-to-end via an 11-gate cycle: detects the stack, audits compliance, then dispatches backend agents to implement tenantId-from-JWT routing through the lib-commons v5 dispatch layer (config, middleware, repositories, metrics, tests) and runs reviewers. Use when…
dt-sec-insights
Query and analyze Dynatrace security data in security.events with DQL: vulnerabilities, threat detections, compliance posture, and scan coverage. Covers Dynatrace-native Runtime Vulnerability Analytics (RVA — CVEs, reachability, exposure, exploit), Runtime Application Protection (RAP), Automated Detections, and…
ring:testing-skills-with-subagents
Hardening a skill so it resists rationalization under pressure: run combined-pressure scenarios on a subagent without the skill (RED), capture excuses verbatim, write/edit the skill (GREEN), then plug loopholes (REFACTOR) until compliance holds. Use when deploying or editing a discipline-enforcing skill that an agent…