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 ciaransaunders/Skills-Public --skill legal-writing-qualitygit clone --depth 1 https://github.com/ciaransaunders/Skills-PublicWrote 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/ciaransaunders/skills-public/legal-writing-quality)<a href="https://agentmods.dev/skills/ciaransaunders/skills-public/legal-writing-quality"><img src="https://agentmods.dev/badge/skills/ciaransaunders/skills-public/legal-writing-quality/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/ciaransaunders/skills-public/legal-writing-quality"><img src="https://agentmods.dev/badge/skills/ciaransaunders/skills-public/legal-writing-quality.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 | $0.00000 | $0.01725 |
| Opus 5 | $0.00000 | $0.00863 |
| Sonnet 5 | $0.00000 | $0.00345 |
| Haiku 4.5 | $0.00000 | $0.00172 |
Grade A, and why
legal-writing-quality 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal Writing Quality
Review, draft, improve, or critique legal writing — including correspondence, case analysis reports, legal memos, skeleton arguments, and other professional legal documents — applying the standards of qualified legal practice in England and Wales.
Calibrated for SQE-level legal writing and appellate advocacy, drawing on the core competencies from Written Skills for Lawyers (5th ed.).
Core Principles — Apply to Everything
Before doing anything else, hold these five principles in mind. Every output you produce should be tested against them.
1. Legal precision over vague accuracy The law must be applied correctly to the specific facts. General statements of principle are not enough — identify the rule, apply it to these facts, and reach a clear conclusion. Never leave the reader to do the application themselves.
2. Clarity and conciseness Prefer plain English. Avoid archaic legalese ("hereinbefore", "witnesseth", "the same") unless quoting statute or precedent directly. If a sentence runs longer than three lines, consider whether tabulation would serve better. Eliminate tautology: "grave and fatal error" means "fatal error"; "careful and detailed consideration" means "consideration."
3. Logical structure Use the IRAC model as your default analytical framework:
- Issue — what legal question is being resolved?
- Rule — what is the applicable legal principle or test?
- Application — how does the rule apply to these specific facts?
- Conclusion — what is the clear outcome or recommendation?
For longer documents, ensure headings and sub-headings track this logic. The reader should never have to search for where the analysis is.
4. Client-focused perspective Legal writing is not an academic exercise. Every analysis should address: what does this mean for the client? What are their options? What are the practical consequences of each? Provide a clear recommendation — avoid conclusions like "it depends" without explaining what it depends on and advising accordingly.
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 · 135 lines · 0 tokens per session scan A 819829a0cdce
legal-writing-quality is a skill published in the GitHub repository ciaransaunders/Skills-Public (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,725 tokens. 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
governance
Manage the openEHR specification governance lifecycle — releases, change requests (CR/PR), and lifecycle states (DEVELOPMENT/TRIAL/STABLE…). This skill should be used when the user asks to create or tag a release, prepare a release branch, update the manifest for a release, submit or manage a CR/PR, promote a spec's…
counsel
Senior Contract Administrator & FIDIC / EPC contract specialist for oil, gas, refining, petrochemical, polymer, and upstream capital works. Use whenever the user mentions contract drafting, contract administration, FIDIC (Red Book / Yellow Book / Silver Book / Pink Book / Gold Book / Emerald Book / White Book), Pearl…
steward
Senior HSE, ESG, and Decarbonisation Specialist for oil & gas, refining, petrochemical, polymer, upstream, and energy projects. Use whenever the user mentions HSE management system (HSE-MS), ISO 14001 environmental management, ISO 45001 occupational health & safety, OHSAS 18001, ISO 50001 energy management, IOGP…
pentest-engagement-planner
Define legal scope, rules of engagement, and authorization artifacts for downstream pentest execution.
legal-firm-ops
Law firm operations and legal vertical workflows — client intake, conflict screening, time tracking, billing narratives, IOLTA, document review, contract risk flagging. Use when the user works at a law firm and asks about prospect qualification, retainer agreements, billable hour capture, trust accounting…
strm-mapping
Use when asked to map, crosswalk, align, compare, or gap-analyze any two cybersecurity frameworks, control catalogs, or regulatory requirements using NIST IR 8477 Set-Theory Relationship Mapping (STRM). Triggers on terms like "map controls", "crosswalk", "framework alignment", "gap analysis", or producing a STRM CSV…