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 KirKruglov/claude-skills-kit --skill company-policy-draftergit clone --depth 1 https://github.com/KirKruglov/claude-skills-kitWrote 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/kirkruglov/claude-skills-kit/company-policy-drafter)<a href="https://agentmods.dev/skills/kirkruglov/claude-skills-kit/company-policy-drafter"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/company-policy-drafter/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/kirkruglov/claude-skills-kit/company-policy-drafter"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/company-policy-drafter.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 | $0.00081 | $0.02108 |
| Opus 5 | $0.00041 | $0.01054 |
| Sonnet 5 | $0.00016 | $0.00422 |
| Haiku 4.5 | $0.00008 | $0.00211 |
Grade A, and why
company-policy-drafter 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company Policy Drafter
This skill drafts or updates a single company policy (PTO, remote work, expenses, or AI-usage) in a structured, handbook-ready format for SMB teams without in-house HR or legal staff. Each output includes a mandatory legal review flag and an optional change-summary when updating an existing policy.
Input:
- Policy type (PTO / remote work / expenses / AI-usage / other)
- Key parameters: limits, rules, exceptions, effective date (optional; placeholders used if missing)
- Existing policy text (optional; triggers update mode with change-summary)
- Language preference: both EN+RU / EN only / RU only (optional; default: both)
Output:
- Bilingual policy document (EN + RU blocks, synchronized structure)
- Mandatory ⚠️ legal review flag
- Change summary section (update mode only)
- Next steps checklist
Language Detection
Detect the user's language from their message:
- If Russian (or contains Cyrillic): respond in Russian
- If English (or other Latin-script language): respond in English
- If ambiguous: respond in the language of the trigger phrase used
Instructions
Step 1: Identify Policy Type
-
Read the user's message and extract the policy type.
- Recognized types: PTO / vacation, remote work / work from home, expenses / reimbursement, AI-usage / AI tools
- Also accept any custom policy type (e.g., "social media policy", "confidentiality policy")
-
If policy type is not specified:
- Stop and ask: "Which policy do you need? Examples: PTO, remote work, expenses, AI-usage, or describe your own."
- Do not proceed until a type is provided.
Step 2: Collect Parameters
-
Extract any parameters the user provided:
- Limits (e.g., "20 days PTO per year", "up to $50 per meal")
- Rules and conditions (e.g., "approval required 2 weeks in advance")
- Exceptions (e.g., "does not apply to contractors")
- Effective date
-
For any missing parameters: use explicit placeholder
[SPECIFY VALUE / УКАЖИТЕ ЗНАЧЕНИЕ]— do not invent values or leave blanks silently.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 219 lines · 81 tokens per session scan A d914d4e742b9
company-policy-drafter is a skill published in the GitHub repository KirKruglov/claude-skills-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 2,108 once invoked, about $0.0004 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 skills, from other repositories
local-legal-seo-audit
Audit and improve local SEO for law firms, attorneys, forensic experts and legal/professional services sites with local presence, focusing on GBP, directories, E-E-A-T and practice/location pages.
security-bluebook-builder
Build a minimal but real security policy for sensitive apps. The output is a single, coherent Blue Book document using MUST/SHOULD/CAN language, with explicit assumptions, scope, and security gates.
security-compliance-compliance-check
You are a compliance expert specializing in regulatory requirements for software systems including GDPR, HIPAA, SOC2, PCI-DSS, and other industry standards. Perform compliance audits and provide implementation guidance.
employee-handbook-builder
TRIGGER THIS when creating or updating employee handbooks, documenting HR policies, developing code of conduct, building benefits guides, or creating leave/PTO policies. Creates comprehensive, legally compliant, accessible employee handbooks covering company policies, culture, benefits, code of conduct, and all…
canned-responses
Generate templated responses for common legal inquiries and identify when situations require individualized attention. Use when responding to routine legal questions — data subject requests, vendor inquiries, NDA requests, discovery holds — or when managing response templates.
contract-negotiation
Prepare for contract negotiations with term analysis, BATNA preparation, negotiation playbooks, and comparison frameworks.