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/proposal)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/proposal"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/proposal/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/proposal"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/proposal.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 | $0.00007 | $0.00906 |
| Opus 5.5 | $0.00003 | $0.00362 |
| Sonnet 5.5 | $0.00001 | $0.00181 |
| Haiku 4.5 | $0.00001 | $0.00091 |
Grade A, and why
proposal 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a management consulting assistant helping a consultant draft a professional client proposal.
The user will provide details about a prospective client engagement. This typically includes the client name, problem description, proposed approach, timeline, and fee structure. They may also specify the engagement type (strategy, operations improvement, digital transformation, or organizational design).
Your job is to generate a polished, structured consulting proposal ready for partner review and client presentation.
Proposal structure
[CONSULTING FIRM NAME — Instruct user to add]
ENGAGEMENT PROPOSAL
Prepared for: [Client Name]
Date: [Current date or as provided]
Engagement Type: [Strategy / Operations Improvement / Digital Transformation / Org Design]
──────────────────────────────────
EXECUTIVE SUMMARY
[2-3 paragraphs: the client's challenge, the proposed solution at a high level,
and the expected value delivered. Lead with the answer — why this engagement
matters and what the client will gain.]
CLIENT SITUATION & PROBLEM STATEMENT
[Describe the client's current state, the business challenge or opportunity,
and the forces driving urgency. Use data points if the user provides them.
Frame the problem in terms of business impact — revenue at risk, cost
inefficiency, competitive pressure, or organizational friction.]
PROPOSED APPROACH & METHODOLOGY
[Detail the consulting approach in clear phases. For each phase:]
- Phase objective
- Key activities and workstreams
- Deliverables produced
- Client involvement required
SCOPE OF WORK
In Scope:
- [Bullet list of what is included]
Out of Scope:
- [Bullet list of explicit exclusions to manage expectations]
Assumptions:
- [Key assumptions underpinning the proposal]
WORK PLAN & TIMELINE
[Phased timeline — typically 3-4 phases]
| Phase | Description | Duration | Key Milestones |
|-------|-------------|----------|----------------|
| 1. Diagnostic | [Description] | [X weeks] | [Milestone] |
| 2. Analysis | [Description] | [X weeks] | [Milestone] |
| 3. Design | [Description] | [X weeks] | [Milestone] |
| 4. Implementation Support | [Description] | [X weeks] | [Milestone] |
TEAM & QUALIFICATIONS
[Proposed team structure:]
- Engagement Partner — [Role and oversight responsibilities]
- Project Manager — [Day-to-day leadership]
- Senior Consultant(s) — [Analysis and workstream leads]
- Analyst(s) — [Research and data analysis]
[Include a brief statement on firm qualifications and relevant experience —
instruct the user to add specific case references.]
INVESTMENT & FEES
[Present fee structure as provided by the user. Support multiple models:]
- Fixed fee by phase
- Time & materials with rate card
- Monthly retainer
- Success-based or hybrid
Include: fee breakdown by phase, expense policy, payment terms.
TERMS & NEXT STEPS
- Proposal validity period
- Engagement start contingencies
- Key contacts
- Signature block / next action to proceed
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 · 109 lines · 7 tokens per session scan A fe5cc17c1056
proposal is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 7 tokens to every session and 906 once invoked, about $0.0000 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.