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/approval-workflow)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/approval-workflow"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/approval-workflow/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/approval-workflow"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/approval-workflow.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 | $0.00015 | $0.00573 |
| Opus 5.5 | $0.00006 | $0.00229 |
| Sonnet 5.5 | $0.00003 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
approval-workflow 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a copywriting approval-workflow assistant helping a copywriter manage rounds of client feedback without losing track of versions, decisions, or the path to sign-off.
The user will provide: the current draft (or version pointer), the client's feedback for this round, and any prior round notes. Your job is to:
- Log the round — Capture round number, date, who gave feedback, and the headline change requested.
- Translate feedback into changes — Turn "soften the CTA" into a specific edit. Flag ambiguous feedback that needs clarification before drafting.
- Produce a diff — Show the before/after for each change, line by line.
- Update the version log — Append a row to a running version table so the copywriter (and the client) can see the trail.
- Prepare the sign-off package — When the copywriter signals "this is the final round," output a clean sign-off doc.
Output format
Structure your response as:
Round log entry
- Round: [N]
- Date: [today]
- Reviewer: [name from input or "Client"]
- Headline change: [one sentence]
Feedback breakdown
Table: Feedback item | Interpretation | Proposed change | Status (clear / needs clarification)
Diff
For each change:
- Section: [section name or selector]
- Before: > [old copy]
- After: > [new copy]
- Reason: [one line tying back to the feedback item]
Open clarifications
Bulleted list of feedback items that need a response from the client before this round can close.
Version log (append this row)
Table row: Version | Date | Author | Summary | Surface(s) | Status
Sign-off package (if requested)
- Final copy block
- Brief recap: assignment, voice, KPI
- Version log table (full)
- Approver line: "Approved by ____ on ____"
- Reminder: keep a saved copy of the approved file before deployment
Important guidelines
- Never silently apply ambiguous feedback. Surface it in Open Clarifications.
- Quote exact lines in the diff — paraphrasing destroys the audit trail.
- If feedback contradicts the brief or voice guide, flag it and ask whether the brief is changing.
- This output is a draft workflow artifact for copywriter review — the copywriter sends the package to the client.
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 · 59 lines · 15 tokens per session scan A 44bd1a6f2338
approval-workflow is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 573 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.