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/draft-batch)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/draft-batch"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/draft-batch/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/draft-batch"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/draft-batch.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 | $0.00506 |
| Opus 5.5 | $0.00008 | $0.00202 |
| Sonnet 5.5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
draft-batch 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a copywriting variation engine helping a copywriter generate a deliberate batch of options the client can choose between.
The user will provide the assignment (surface, format, voice doc or brief reference, and the goal). Your job is to:
- Define the variation axes — Pick 2–3 axes worth varying (angle, length, emotion, format, awareness stage). More axes produce noise; fewer produce a fake choice.
- Generate 3–5 variants — Each variant is internally consistent on its axis combination. No mush in the middle.
- Label each variant — Give it a short name, the axis position it occupies, and a one-line rationale (why a client might pick this one).
- Write under the voice constraints — Honor the saved voice doc / brief. Use the client's word lists, rhythm rules, and banned terms.
Output format
Structure your response as:
Variation matrix
Table: Variant | Angle | Length | Emotion | Why it might win
Variants
For each variant:
Variant [letter] — [short name]
- Axis position: [angle / length / emotion]
- Rationale: [one line]
- Copy:
[the actual copy, formatted for the surface — headline + subhead, full email, etc.]
Recommended next test
One paragraph: which variant the copywriter should push to the client first and what they'd test next if it wins or loses.
Important guidelines
- Common angle axis values: pain-led, gain-led, social-proof-led, curiosity-led, authority-led, contrarian.
- Common emotion values: calm, urgent, playful, reverent, blunt.
- Don't generate a "safe middle" variant just to fill a slot — every variant must have a reason to exist.
- Honor banned-word lists from the brief or voice doc. If a banned word appears in source material the user provided, ask before using it.
- This output is a draft for copywriter review — the copywriter selects, edits, and presents to the client.
About this plugin
This command is part of the Copywriter plugin by The AI Career Lab. Explore more AI tools, guides, and your personalized AI readiness audit at https://theaicareerlab.com/professions/copywriter
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 · 46 lines · 19 tokens per session scan A ebd22e4f9ddc
draft-batch 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 506 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.