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 demand-lettergit 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/demand-letter)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/demand-letter"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/demand-letter/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/demand-letter"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/demand-letter.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 | $0.00045 | $0.02711 |
| Opus 5 | $0.00023 | $0.01355 |
| Sonnet 5 | $0.00009 | $0.00542 |
| Haiku 4.5 | $0.00005 | $0.00271 |
Grade A, and why
Demand Letter 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 10d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demand Letter
Purpose
Produce a structured draft demand letter for attorney review, revision, and sending. The skill works in three stages — intake, a pre-draft risk gate, and drafting — so that strategic and privilege questions are settled before any letter text is written. It organizes the factual narrative, identifies the claimed basis for relief, articulates a specific demand, and flags every legal conclusion, damages figure, response deadline, and consequence of non-response as an item requiring attorney confirmation. The draft is not a final negotiating position and must not be sent without attorney review and approval.
Use When
- A user asks to "draft a demand letter," "write a demand," or "send a letter before filing suit."
- Counsel wants a structured first draft before editing and sending a pre-litigation demand.
- A client has suffered a harm and counsel needs to frame and communicate a pre-suit demand.
- A breach of contract, tort claim, employment dispute, property damage, or similar matter requires a formal written demand as a precursor to litigation or negotiation.
- A statutory or contractual pre-suit notice requirement must be met (attorney must confirm applicability and form).
Required Inputs
- The client's identity and role (the party making the demand).
- The recipient's identity and, if known, address and counsel information.
- A description of the dispute, the alleged harm, and the factual background (from documents or a client summary).
- The nature of the claim or legal theory to be asserted (e.g., breach of contract, negligence, fraud) — attorney will confirm.
- The relief or remedy being demanded (e.g., payment of a specific amount, return of property, specific performance).
- Any prior correspondence on the matter, and the underlying contract or authority (pasted in full where possible, not summarized).
- The desired posture: tone (measured / firm / aggressive), the response window, how the letter will be sent, and who will sign it.
What ships with it
1 file 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.
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.
- 10d ago First seen · 149 lines · 45 tokens per session scan A f9027c43b099
Demand Letter is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 2,711 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 2026-08-30.
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.
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.
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.…
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.