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 written-consentgit 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/written-consent)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/written-consent"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/written-consent/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/written-consent"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/written-consent.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 | $0.00030 | $0.03209 |
| Opus 5 | $0.00015 | $0.01605 |
| Sonnet 5 | $0.00006 | $0.00642 |
| Haiku 4.5 | $0.00003 | $0.00321 |
Grade A, and why
Written Consent 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Written Consent
Purpose
Produce a structured, attorney-ready draft of a corporate action taken by written consent in lieu of a meeting. The skill drafts the consent instrument — recitals, resolved paragraphs, and signature blocks — classifies the action as routine or major, flags any director conflicts, and surfaces open verification items. It produces draft legal work product for attorney review — not legal advice, not an executed corporate record, and not authorization to act.
Use When
- A user asks to "draft a written consent," "prepare a board consent," or "document a board action in lieu of a meeting."
- The board of directors or a board committee is taking a formal action outside a meeting and needs a consent instrument to evidence that action.
- The user has a specific corporate action to document — for example, an officer appointment, an equity grant, a financing approval, or a contract authorization — and the relevant body is acting by written consent rather than at a noticed meeting.
- A precedent consent is available for format reference and the user wants to conform the draft to the company's house style.
Required Inputs
- Action description. A clear, one-sentence description of the action being approved (e.g., "appointment of Jane Smith as Chief Financial Officer effective June 1").
- Supporting detail. Names, titles, amounts, counterparty identities, and any specific agreement or instrument that the action authorizes, approves, or references. The more detail provided, the more precise the recitals and resolved paragraphs can be.
- Effective date. The date on which the consent is to take effect. If not provided, flag as
[CONFIRM: effective date]and note that the effective date is a legal determination in some jurisdictions. - Signatories. The full board, a named committee, or a specific subset, with each signatory's full name and title. If not provided, the draft cannot include accurate signature blocks; stop and request this information.
- Director conflicts. Whether any signatory has a disclosed financial or other interest in the action. Even a "none known" confirmation is useful.
- Optional — precedent consent. A prior consent from the company for format and house-style reference. If not provided, the draft uses the neutral standard form in
templates/written-consent-outline.mdand flags it to be conformed to house style. - Optional: the practice group's
practice-profiles/corporate.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 and resolution-form defaults. If absent, the skill proceeds without practice-profile benchmarking and asks the user to supply standing positions inline if needed.
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 · 140 lines · 30 tokens per session scan A 8b3190d56f16
Written Consent is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 3,209 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
document-fill
A document-filling assistant that uses a supplied template and case files to fill in forms, contracts, or legal documents. It also reports where each filled value came from and which details are missing.
treatment-plans
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
fill-icmje-coi
Batch-generate per-author ICMJE Conflict of Interest Disclosure Forms (coidisclosure.docx) for manuscript submission. Pre-fills all 13 disclosure items as "☒ None" + final certification ☒ using a synthetic seed template shipped with the skill, then clones the seed per author with Date, Name, and Manuscript Title…
law-to-markdown
A legal-document conversion skill for turning PDF, Word, or plain-text regulations into structured Markdown. Markdown is a text format that uses simple symbols for headings and lists.
cowork-data-room-builder
Prepare YOUR data room for a fundraise, acquisition, or bank diligence -- builds the checklist for your deal stage, sweeps your folders for what you already have, produces a gap report, and organizes everything into the structure buyers and investors expect. The sell-side complement to cowork-deal-room.
signature-request
Pre-signature gate and routing plan for a finalized document — verifies exact legal entity names, signatory authority, attached exhibits, filled blanks, consistent dates, and counterparty details, then sets the signing order (sequential vs. parallel, with reasons), writes envelope instructions for any e-sign tool, and…