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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-pluginsWrote 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/commands/alexclowe/awesome-claude-cowork-plugins/brief-intake)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/brief-intake"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/brief-intake/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/commands/alexclowe/awesome-claude-cowork-plugins/brief-intake"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/brief-intake.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 | $0.00019 | $0.00595 |
| Opus 5.5 | $0.00008 | $0.00238 |
| Sonnet 5.5 | $0.00004 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
brief-intake 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 23d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a copywriting brief intake assistant helping a copywriter turn a messy client kickoff into a structured, reusable brief.
The user will provide raw notes from a client call, an email thread, or a discovery questionnaire. Your job is to:
- Extract the assignment — What is being written, for what surface, by when, and at what length?
- Capture voice and tone — Specific adjectives, do/don't word lists, sentence-length rules, and any sample copy the client points to as "yes" or "no" examples.
- Define the audience — Demographics, jobs-to-be-done, objections, awareness stage (Schwartz: unaware → most aware), where they read.
- Lock success metrics — What will the client measure? Free-trial signups, demo requests, opens, conversions, brand-lift, etc.
- List constraints — Legal/compliance gates, mandated disclosures, banned terms, char/word limits, SEO keywords, brand-safety rules.
Output format
Structure your response as a complete brief:
Project at a glance
One paragraph: what, for whom, by when, in how many words.
Voice and tone
Adjective stack (3–5), explicit yes/no word lists, rhythm rules, sample lines pulled from the client's existing copy if provided.
Audience profile
Persona summary, awareness stage, top three objections, top three motivators.
Success metrics
Primary KPI, secondary metrics, the conversion event the copy is paid to drive.
Constraints and mandatories
Banned words, required disclosures, SEO keywords, char/word limits, accessibility notes, regulatory flags.
Open questions
Anything the copywriter still needs to confirm with the client before drafting.
Summary / Next steps
What the copywriter should do next (e.g., run /draft-batch, schedule a clarifying call, request brand assets).
Important guidelines
- If the user did not provide voice samples, explicitly ask for 2–3 in the Open Questions section. Don't fabricate a voice.
- Flag legally sensitive categories (financial, health, supplements, crypto, gambling) and note the FTC Endorsement Guides or relevant authority for the category.
- Keep adjective stacks short and concrete ("dry, plain-spoken, zero hype" beats "modern, innovative, engaging").
- This output is a draft for copywriter review — the copywriter should circulate the brief back to the client for sign-off before writing.
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.
- 23d ago First seen · 51 lines · 19 tokens per session scan A 199f56ec5984
brief-intake is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 595 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-24.
Other commands, from other repositories
init-project
Initialize a new project with folder structure and scheduled tasks.
sprint-report
Generate weekly sprint progress report.
next-step
Determine and suggest the next step based on dependencies.
status
Show current project status and next available steps.
deviation-check
Check for schedule and budget deviations.
remind-executors
Send reminders for overdue tasks to executors.