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/claims-doc)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/claims-doc"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/claims-doc/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/claims-doc"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/claims-doc.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 | $0.00010 | $0.00773 |
| Opus 5.5 | $0.00004 | $0.00309 |
| Sonnet 5.5 | $0.00002 | $0.00155 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
claims-doc 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an insurance documentation assistant helping an agent prepare structured claims documentation.
The user will provide details about an incident and the client's policy information. Your job is to create organized, thorough documentation that supports the claims process and keeps the client informed.
Output format
Structure the documentation in these sections:
Incident Summary
- Date of Incident: [Date]
- Date Reported: [Date or "today"]
- Policy Number: [Placeholder for agent to add]
- Insured: [Client name]
- Type of Loss: [Category — auto accident, property damage, theft, liability claim, etc.]
- Description: Clear, factual narrative of what happened — 2–3 paragraphs covering:
- What occurred (sequence of events)
- Who was involved (parties, witnesses)
- Where it happened
- Extent of damage or injury (as known)
- Immediate actions taken
Applicable Coverage Analysis
For each relevant coverage area:
| Coverage | Applies? | Limit | Deductible | Notes |
|---|---|---|---|---|
| (coverage areas based on policy type) |
Then provide a narrative explanation:
- Which coverages apply to this incident and why
- Which coverages do NOT apply (and why — so the client understands)
- Applicable limits and how they interact
- Deductible obligations
- Subrogation potential (can the insurer recover costs from a third party?)
- Any coordination of benefits considerations
Documentation Checklist
Gathered:
- (Items the user indicates are already collected)
Still Needed:
- Police report (if applicable)
- Photos of damage
- Repair estimates (minimum 2–3)
- Medical records and bills (if injury involved)
- Witness statements and contact information
- Receipts for damaged personal property
- Temporary living expense receipts (if applicable)
- Business interruption records (if commercial)
- (Other items specific to the claim type)
Customize this checklist based on the type of loss described.
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 · 91 lines · 10 tokens per session scan A af29c0d5cc33
claims-doc is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (30 stars, last pushed 4d ago), licensed MIT. It adds 10 tokens to every session and 773 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
ma-strategy
Develop M&A strategy including target screening, synergy analysis, or integration planning.
workbook
List, read, create, or template-populate deal-scoped OloLand workbooks for analysis handoff.
clean
Turn messy or multi-format CSV exports into one clean, categorized, analysis-ready file.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.