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.
npx skills add latestaiagents/agent-skills --skill policy-document-writergit clone --depth 1 https://github.com/latestaiagents/agent-skillsWrote 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/skills/latestaiagents/agent-skills/policy-document-writer)<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/policy-document-writer"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/policy-document-writer/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/skills/latestaiagents/agent-skills/policy-document-writer"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/policy-document-writer.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 | $0.00054 | $0.02097 |
| Opus 5 | $0.00027 | $0.01048 |
| Sonnet 5 | $0.00011 | $0.00419 |
| Haiku 4.5 | $0.00005 | $0.00210 |
Grade A, and why
policy-document-writer 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 6d 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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Policy Document Writer
Create clear, legally compliant HR policies and handbook content.
When to Use
- Writing new company policies
- Updating employee handbooks
- Ensuring policy compliance
- Communicating policy changes
- Standardizing workplace guidelines
Policy Document Structure
Standard Policy Template
# [Policy Name]
**Effective Date:** [Date]
**Last Updated:** [Date]
**Policy Owner:** [Department/Role]
**Applies To:** [All employees / Specific groups]
## Purpose
[Why this policy exists - 1-2 sentences]
## Scope
[Who this policy applies to and when]
## Policy Statement
[The actual policy rules and guidelines]
## Procedures
[Step-by-step processes for implementing the policy]
## Responsibilities
[Who is responsible for what]
## Definitions
[Key terms defined]
## Related Policies
[Links to related policies]
## Questions
[Contact information for questions]
---
*This policy is subject to change. Employees will be notified of updates.*
Common Policy Templates
Remote Work Policy
# Remote Work Policy
**Effective Date:** [Date]
**Applies To:** All eligible employees
## Purpose
This policy establishes guidelines for remote work arrangements to support flexibility while maintaining productivity and collaboration.
## Eligibility
Remote work may be available to employees who:
- Have completed their probationary period
- Demonstrate ability to work independently
- Have job responsibilities compatible with remote work
- Have reliable internet and appropriate workspace
## Types of Remote Work
1. **Fully Remote:** Work from home 100% of the time
2. **Hybrid:** Split time between office and remote (e.g., 3 days office, 2 days remote)
3. **Occasional Remote:** As-needed flexibility with manager approval
## Expectations
### Work Hours
- Core hours: [e.g., 10 AM - 3 PM local time] for meetings and collaboration
- Flexible hours outside core hours to complete full workday
- Response time: Within [X hours] during work hours
### Communication
- Keep calendar updated with availability
- Be reachable via Slack/Teams during work hours
- Camera-on for team meetings unless otherwise agreed
- Attend required in-person meetings/events
### Workspace Requirements
- Dedicated workspace with minimal distractions
- Reliable high-speed internet
- Secure, private environment for confidential work
### Equipment
- Company will provide: [laptop, monitor, etc.]
- Employee responsible for: [internet, furniture, etc.]
- Reimbursement available for: [specify items and limits]
## Security
- Use company VPN for all work
- Lock computer when stepping away
- Do not work from public WiFi without VPN
- Report any security concerns immediately
## Performance
- Performance expectations remain the same as in-office
- Regular check-ins with manager
- Participation in team meetings and activities
## Approval Process
1. Discuss with direct manager
2. Complete remote work agreement form
3. HR review and approval
4. Annual renewal required
## Termination of Remote Work
The company may modify or revoke remote work arrangements based on:
- Business needs
- Performance concerns
- Policy violations
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.
- 6d ago First seen · 356 lines · 54 tokens per session scan A 49cae6e19c1e
policy-document-writer is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 2,097 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
ai-ad-copy-compliance-review
A risk-review assistant for advertising and sales copy. It examines provided material for possible concerns and suggests actions.
ai-financial-marketing-compliance-review
A financial marketing compliance review assistant for examining pricing or marketing material for financial concerns.
ai-insurance-policy-faq-explainer
A risk-review helper for explaining questions about insurance policies and their possible risks. It produces summaries, diagnoses, recommended actions, and reusable deliverables from supplied material.
ai-live-commerce-script-compliance-review
A risk review assistant for checking provided live-commerce scripts and producing findings, recommendations, and reusable review materials.
ai-pharma-visit-material-compliance-review
A compliance review assistant for checking pharmaceutical visit materials for possible risks. Compliance means following the rules that apply to professional or regulated communication.
ai-policy-execution-checklist-generator
A policy risk review assistant that turns supplied policy material into an execution checklist. A policy is a set of rules or guidance for how an organisation should act.