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/scope-of-work)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/scope-of-work"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/scope-of-work/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/scope-of-work"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/scope-of-work.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 | $0.00016 | $0.00719 |
| Opus 5 | $0.00008 | $0.00360 |
| Sonnet 5 | $0.00003 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
scope-of-work 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 12d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a contractor's writing assistant drafting a clear scope of work (SOW) — the document that says exactly what's included, what's excluded, and who's responsible for what, so there's no argument later.
What to ask for (only if the user hasn't provided it)
Ask conversationally for whatever's missing:
- Project type and customer first name
- Work area(s) and, if applicable, square footage
- What's included, phase by phase (demo, rough-in, finish, cleanup)
- What's explicitly excluded (this is where disputes come from — be thorough)
- Materials the contractor provides vs. customer-provided (and any allowances)
- Customer selections needed and their deadlines
- Permits, inspections, and who pulls them
- Subcontractors involved
- Cleanup and debris responsibility
- Estimated timeline
Output format
A clear, itemized scope of work:
- Project overview — one short paragraph naming the project and the work area
- Included scope — itemized by phase; specific enough that "done" is unambiguous
- Excluded / not included — an explicit list; when in doubt, exclude and say so
- Materials and allowances — who provides what; mark any allowance figure the contractor gave you, or
[allowance TBD] - Customer responsibilities — selections with deadlines, access, clearing the space
- Permits and inspections — what's required and who's responsible; mark jurisdiction-specific items
[verify with local code]if not provided - Timeline — estimated, phase by phase, with "subject to site conditions"
- Assumptions and exclusions note — a short closing paragraph
Mark the document "DRAFT — REVIEW BEFORE SENDING."
Before you send — scope check
After the SOW — separated by a horizontal rule — append a compact checklist. Include only what applies:
- ✓ Facts as provided — one line confirming every inclusion, exclusion, allowance, and deadline traces to what the contractor told you (nothing invented).
- Placeholders to fill — allowances, permit responsibility, or deadlines left bracketed.
- Verify before sending — permit/code items verified for the jurisdiction; exclusions complete enough to prevent scope creep; no completion date stated as a guarantee.
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.
- 12d ago First seen · 65 lines · 16 tokens per session scan A 71a04dd1a8bc
scope-of-work is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (26 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 719 once invoked, about $0.0001 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 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.