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 zgbrenner/agentcounsel --skill brief-section-draftergit clone --depth 1 https://github.com/zgbrenner/agentcounselWrote 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/zgbrenner/agentcounsel/brief-section-drafter)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/brief-section-drafter"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/brief-section-drafter/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/zgbrenner/agentcounsel/brief-section-drafter"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/brief-section-drafter.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 | $0.00055 | $0.04279 |
| Opus 5 | $0.00028 | $0.02139 |
| Sonnet 5 | $0.00011 | $0.00856 |
| Haiku 4.5 | $0.00006 | $0.00428 |
Grade A, and why
Brief Section Drafter 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brief Section Drafter
Purpose
Produce a first draft of a single section of a litigation brief for attorney review, revision, and sign-off. The draft is cited to the record, internally consistent with the case theory, and marked throughout with verification placeholders wherever legal authority or factual accuracy must be confirmed. It is draft legal work product for attorney review; it is not legal advice. The draft is never filed unreviewed.
This skill does not decide litigation strategy, invent legal authority, or produce a final, file-ready document. It writes disciplined, honest prose that gives the supervising attorney a solid working draft — not a shortcut around professional judgment.
Use When
- Counsel needs a first draft of a specific brief section: a statement of facts, an argument section or sub-section, a standard of review section, a conclusion, or a similar discrete component of a written submission.
- A user asks to "draft the argument section," "write the statement of facts," or "put together the standard-of-review section."
- The case theory and the relevant record materials are available and can be provided as inputs.
- The matter is in active litigation or an imminent filing posture and the section type is known.
- The draft is for a written submission (motion, opposition, brief, reply) or, with appropriate scope adjustment, a structured outline for oral argument preparation.
Required Inputs
- Matter identification — matter name, matter number, or a brief description sufficient to identify the case.
- Case theory — one sentence stating the factual and legal proposition the filing party is advancing. The entire draft turns on this sentence; without it, the skill cannot produce a coherent section.
- Section type — the specific section to be drafted: statement of facts, argument (identify the proposition), standard of review, conclusion, or another named section. If the section type is ambiguous, the skill will ask for clarification before drafting.
- Written submission or oral argument — confirm which posture applies. Written submissions call for thorough authority development with full citation placeholders; oral argument preparation produces a leaner structure with a sharper lead and fewer supporting points.
- Forum and local rules — paste the relevant local rules, standing orders, or page and word-count limits directly into the input. If this material is not provided, the skill will flag all format and length requirements as
[CONFIRM: forum rules not provided — attorney to verify]. Do not rely on the skill's background knowledge of any court's rules; treat all unstated rules as unconfirmed. - House style sample — a sample brief or excerpt from the supervising attorney or firm showing the expected tone, heading style, citation format, and prose register. If none is provided, the skill will note the absence and apply a neutral, professional default, flagging the style choice for attorney review.
- Record materials — the documents, deposition transcripts, declarations, pleadings, or other record items that will supply the factual predicate for this section. Every fact in the draft must be tied to a provided record item or flagged
[VERIFY: record cite needed]. If no record materials are provided, the skill cannot draft a fact-intensive section and will stop to request them. - Authorities already identified by counsel — any cases, statutes, rules, or secondary sources that the supervising attorney has already confirmed and directed the skill to use. The skill will insert these as placeholders in the proper locations; it will not add authority beyond what is provided and directed.
- Optional: the practice group's
practice-profiles/litigation.mdif it has been populated and is loaded alongside this skill. If present, the skill uses its Preferred Output Style and Standard Positions tables to benchmark the draft against the group's house style. If absent, the skill proceeds without practice-profile benchmarking and asks the user to supply standing positions inline if needed.
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 · 180 lines · 55 tokens per session scan A a33a48846ca9
Brief Section Drafter is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 4,279 once invoked, about $0.0003 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
legaltech-expert
Expert in legal technology: contract lifecycle management, e-discovery, AI-assisted legal research, case and matter management, document automation, and compliance tooling. Use when the user mentions legal case or matter management, e-discovery and legal holds, CLM or contract review and obligation tracking, legal…
uk-particulars-of-claim-review
Use when users say "review these Particulars of Claim", "check this PoC", "pleading gaps", "CPR 16", "PD16", "limitation issue", or need England and Wales pleadings checked for elements, material facts, remedies, parties, source support, and drafting risk.
uk-witness-statement-review
Use when users say "review this witness statement", "check this statement before service", "PD 57AC", "statement of truth", "hearsay in this witness evidence", or need England and Wales witness evidence checked for source support, CPR/PD issues, exhibits, chronology conflicts, or argument.
cookie-consent-policy
Drafts publication-ready cookie policies, banner copy, and consent-flow language under GDPR/ePrivacy, CCPA/CPRA, and major U.S. state privacy laws. Converts a verified cookie inventory into enforceable policy sections with lawful-basis mapping, granular opt-in controls, withdrawal mechanics, and user-rights handling.…
dsar-form
Drafts a GDPR- and CCPA-compliant Data Subject Access Request (DSAR) intake form for collecting requester information and processing privacy rights. Use when drafting DSAR forms, privacy rights request templates, or data subject rights workflows for EU/US-regulated organizations.
legal-research
A legal research skill for finding and analysing laws and court cases, including similar cases. It requires access to a reliable legal research database before producing a formal report.