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 LegalQuants/lq-skills --skill lq-governance-playbook-benchmarkgit clone --depth 1 https://github.com/LegalQuants/lq-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/legalquants/lq-skills/lq-governance-playbook-benchmark)<a href="https://agentmods.dev/skills/legalquants/lq-skills/lq-governance-playbook-benchmark"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/lq-governance-playbook-benchmark/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/legalquants/lq-skills/lq-governance-playbook-benchmark"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/lq-governance-playbook-benchmark.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 | $0.00075 | $0.01588 |
| Opus 5 | $0.00037 | $0.00794 |
| Sonnet 5 | $0.00015 | $0.00318 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
lq-governance-playbook-benchmark 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LQ Governance Playbook Benchmark Protocol
You are benchmarking a target governance document against the LQ Governance Playbook. The Playbook is a reference document produced by LegalQuants encoding their preferred positions on recurring board-level clauses.
Inputs Required
- Target document — the currently open Word document under review
- LQ Governance Playbook — must be available as a connected file in the session (uploaded via the "+" button, or open in another Office app). The Playbook will have seven numbered items, each with Preferred / Fallback / Red flag tiers.
If the Playbook is not in the session, stop and ask the user to upload it. Do not attempt to benchmark from memory or general knowledge of governance norms.
Delegation Threshold
This skill produces a draft for legal counsel review. The five-tier classification (Match / Partial Match / Below Fallback / Red Flag / Omitted) and every proposed tracked-change amendment are proposals only. The reviewing lawyer must accept or reject each tracked change before circulation, and owns every change they accept. Ambiguous classifications must be flagged for human decision, not auto-resolved: if the locate or classify step is genuinely contested, mark the row Low-band (see Confidence Bands) and escalate to the user rather than picking a tier.
Confidence Bands
Every row of the classification table carries a confidence band on the locate-and-classify step (independent of the finding taxonomy itself):
- H (High) — provision is unambiguously located, classification is uncontested against the Playbook tier definitions.
- M (Medium) — provision located but classification involves judgement (e.g. partial overlap with two tiers, defined-term mismatch that does not change substance). Proceed but mark for lawyer attention.
- L (Low) — locate step is ambiguous (provision arguably maps to two Playbook items, or target uses a governance model the Playbook does not contemplate), or classification is genuinely contested.
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 · 106 lines · 75 tokens per session scan A 9aa0405c04d4
lq-governance-playbook-benchmark is a skill published in the GitHub repository LegalQuants/lq-skills (54 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 1,588 once invoked, about $0.0004 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 skills, from other repositories
achieving-cmmc-level-2-compliance
Prepare a defense-contractor environment for CMMC Level 2 certification: scope CUI and FCI, implement the 110 NIST SP 800-171 Rev 2 security requirements across 14 families, compute the SPRS score with the DoD Assessment Methodology, manage a compliant POA&M, and ready the organization for a C3PAO assessment. Use when…
implementing-gdpr-data-protection-controls
The General Data Protection Regulation (EU) 2016/679 (GDPR) is the EU's comprehensive data protection law governing the collection, processing, storage, and transfer of personal data. This skill cover.
implementing-pci-dss-compliance-controls
PCI DSS 4.0.1 establishes 12 requirements across 6 control objectives for organizations that store, process, or transmit cardholder data. With PCI DSS 3.2.1 retiring April 2024 and 51 new requirements.
compliance
Use when scoping which regulatory frameworks bind a business — SOC 2, ISO 27001, HIPAA, PCI DSS, EU AI Act, DORA, NIS2 — building a control register with owners and evidence, or standing up the cadence that keeps it audit-ready. NOT drafting privacy-policy/ROPA/DPA or ToS text (that is gdpr-privacy, terms-conditions)…
Agent Compliance & Security Assessment
Comprehensive compliance and security self-assessment for AI agents. 14-check framework producing a structured threat model + compliance report with RED/AMBER/GREEN ratings across security, governance, EU AI Act readiness, oversight quality, and NIST alignment domains. Includes automation bias detection, audit trail…
Compliance Checker
Check regulatory compliance across finance, tax, employment, data privacy, and industry-specific requirements.