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 joe-broadhead/open-cowork --skill openwiki-policy-safe-editinggit clone --depth 1 https://github.com/joe-broadhead/open-coworkWrote 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/joe-broadhead/open-cowork/openwiki-policy-safe-editing)<a href="https://agentmods.dev/skills/joe-broadhead/open-cowork/openwiki-policy-safe-editing"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/openwiki-policy-safe-editing/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/joe-broadhead/open-cowork/openwiki-policy-safe-editing"><img src="https://agentmods.dev/badge/skills/joe-broadhead/open-cowork/openwiki-policy-safe-editing.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 | $0.00036 | $0.00352 |
| Opus 5 | $0.00018 | $0.00176 |
| Sonnet 5 | $0.00007 | $0.00070 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade A, and why
openwiki-policy-safe-editing 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.
What it actually says
OpenWiki Policy-Safe Editing
Use this skill when a task touches private Spaces, sensitive records, policy changes, or ambiguous access boundaries.
Required behavior:
- Treat absence from search or graph results as an access boundary, not proof that a record does not exist.
- Do not reveal private record names, paths, snippets, or source titles to users who cannot read them.
- Prefer proposal-mode edits. Policy changes must use policy proposal tools.
- Use CLI, HTTP, or UI policy preview when changing Space paths, grants, approval rules, or target paths; MCP agents should read policy and propose policy changes through the exposed proposal tools.
- Keep proposal rationale free of hidden record names unless the requester has permission to read them.
- Never copy private content into a public page to “make the link work.”
For graph work, inspect edge metadata when available. page_typed_link edges may be explicit or derived; do not promote derived relationships to canonical text without review.
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 · 25 lines · 36 tokens per session scan A 5c7bde19c445
openwiki-policy-safe-editing is a skill published in the GitHub repository joe-broadhead/open-cowork (11 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 352 once invoked, about $0.0002 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
hr-offboard
Generate an offboarding checklist with state-by-state final-pay timing matrix, federal-vs-state-mini-COBRA routing, OWBPA/ADEA-compliant separation-agreement scaffolding for age 40+, McLaren Macomb-compliant non-disparagement, and data-preservation step before access revocation. Templates only - not employment-law…
legal-cease-and-desist
Generate a cease-and-desist letter - trademark, copyright, IP misuse, defamation, breach of contract, or debt - with appropriate tone (professional / firm / litigation-threat), supporting evidence section, demand, and deadline. Templates only - not legal advice. High-stakes versions warrant attorney review before…
legal-contractor
Generate an independent contractor / consulting agreement template - with worker-classification gate (IRS 20-factor + ABC + IR35), 1099 vs W-2 framing, IP assignment, payment terms, and exclusivity. Templates only - not legal advice. Misclassification carries six-figure exposure; have an attorney review before signing.
legal-eula
Generate an End-User License Agreement (EULA) - license grant, restrictions, ownership, warranty disclaimer, app-store-specific addenda (Apple App Store / Google Play). Distinct from Terms of Service. Templates only - not legal advice. Have an attorney review before publication.
legal-compliance-reviewer
Becomes a senior compliance analyst who reviews regulatory requirements, maps controls to frameworks like GDPR and CCPA, and produces gap analyses with remediation recommendations. Use when the user asks for compliance audits, regulatory gap analysis, contract review methodology, or policy review. Do NOT use when the…
finance-r-and-d-credit
Form 6765 R&D Tax Credit walkthrough plus §174 capitalization rules (post-TCJA mandate, software-SMB hot topic). Inputs qualified research activities, qualified research expenses (wages, supplies, contract research), four-part test screening. Outputs 6765 prep package + §174 capitalization schedule. Templates only …