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 nthnclrk/enablement-skills --skill content-governance-systemgit clone --depth 1 https://github.com/nthnclrk/enablement-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/nthnclrk/enablement-skills/content-governance-system)<a href="https://agentmods.dev/skills/nthnclrk/enablement-skills/content-governance-system"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/content-governance-system/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/nthnclrk/enablement-skills/content-governance-system"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/content-governance-system.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 | $0.00063 | $0.00989 |
| Opus 5.5 | $0.00025 | $0.00396 |
| Sonnet 5.5 | $0.00013 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
content-governance-system 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 24d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content governance system
Give content owners a manageable way to keep enablement material accurate, approved, and easy to find.
Fails. "Classify all 400 assets, stand up a content council, and review everything quarterly."
Passes. "Each Wednesday: owners clear due and overdue reviews, intake picks one request, publishers ship only approved versions. Live assets stay published while overdue for review. Urgent launch changes use a 48-hour exception with a named follow-up owner."
A one-time coverage audit and backlog is content-gap-analysis.
Inputs
Reuse supplied context first. If a missing company fact would change the result, check the relevant sections of .enablement/context.md when available. Preserve source dates and approval limits.
Ask only for the inputs that change the operating model:
- Repositories and content types in scope
- Who already owns accuracy, claim approval, and the right to publish
- Current pain: sprawl, stale claims, unclear source of truth, or blocked launches
- Who will own recurring review and publishing work, and how much time they have
If ownership or system-write authority is unknown, leave it unknown. Do not invent usage.
Supporting material
Read references/governance-model-template.md for publication and review states, approval boundaries, and a sustainable operating cadence. Read references/source-system-guide.md when the rules must map into publishing systems the team already uses.
Procedure
- Set a workable review rhythm. Name the owner, decisions, time budget, and events that require attention. Use an existing cadence where it works. A small team may review asynchronously; proposed dates and service levels need owner confirmation.
- Set decision rights. Content approval, publish authorization, and system write are three different rights. A claim owner may approve wording and still lack permission to publish.
- Keep two independent axes.
Publication:
draft,in_review,approved,published,retired. Review:current,due,overdue,blocked. A live asset stayspublishedwhile due or overdue. Review status must not hide it from published denominators. - Trigger review from risk, not a universal calendar. Legal, security, pricing, and product claims need review when their source changes or validity ends. If a published asset contains a known harmful or unauthorised claim, propose a targeted withdrawal or correction to its authorised owner; an overdue date alone does not justify retirement.
- Define intake that matches capacity. One prioritization path for new requests. No shadow queues. Urgent work uses a time-boxed exception that cannot skip legal or security approval.
- Name the quality checks that can fail a publish. Message accuracy, proof, audience, compliance. Cosmetic checks that nobody enforces do not go in the model.
- Separate canonical source from distribution copies. One content ID and version. Changes happen in the canonical source, then propagate. Do not create a second source of truth to "make it easier to find."
- Scale to the team you have. Unused councils, unused gates, and unused metadata fields are failed governance. Measure current-content rate, orphan rate, and review completion — not a usage number you do not have.
What ships with it
3 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.
- 24d ago Changed · +2 lines 58132d55c5e2
- 2mo ago First seen · 74 lines · 63 tokens per session scan A 0597a00f328a
content-governance-system is a skill published in the GitHub repository nthnclrk/enablement-skills (16 stars, last pushed 25d ago), licensed MIT. It adds 63 tokens to every session and 989 once invoked, about $0.0003 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 2026-08-30.
content-governance-system compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| content-governance-systemnthnclrk/enablement-skills | Skill | 16 | 25d ago | MIT | A | 63 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |