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 xonika9/agent-skills --skill x9-okf-docsgit clone --depth 1 https://github.com/xonika9/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/xonika9/agent-skills/x9-okf-docs)<a href="https://agentmods.dev/skills/xonika9/agent-skills/x9-okf-docs"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-okf-docs/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/xonika9/agent-skills/x9-okf-docs"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-okf-docs.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 | $0.00115 | $0.00447 |
| Opus 5 | $0.00057 | $0.00224 |
| Sonnet 5 | $0.00023 | $0.00089 |
| Haiku 4.5 | $0.00012 | $0.00045 |
Grade A, and why
x9-okf-docs 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 9d 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
OKF documentation
Own the current OKF metadata contract so repositories do not copy version-specific fields into AGENTS.md. Preserve document bodies, operate only on explicit scope, and never invent provenance or trust signals.
The machine-readable onboarding contract lists external prerequisites.
Choose one route
- For a new document or a substantive edit, read maintain.md.
- For initial adoption or metadata repair, read adapt-repair.md.
- For an audit, bulk legacy migration, or bundle version declaration, read migration.md.
- For field semantics or authoring new frontmatter, read okf-format.md.
- Use markup-agent-prompt.md only for a read-only metadata proposal.
Do not load unrelated routes. index.md and log.md are reserved OKF files; AGENTS.md, CLAUDE.md, and GEMINI.md are repository instructions, not OKF concepts.
Runtime
The package-owned skills/x9-okf-docs directory is canonical for Claude Code and Codex. Its scripts require Python 3 and Ruby with Psych. Resolve script paths from this loaded skill directory.
Completion
The selected route must leave only the intended files changed, preserve body bytes, BOM, and line endings where metadata tooling runs, and produce passing route-specific validation. Report any unavailable dependency or repository-policy update as DEGRADED.
What ships with it
12 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.
- references/adapt-repair.md 1.5 KB
- references/maintain.md 2.0 KB
- references/markup-agent-prompt.md 1.9 KB
- references/migration.md 1.6 KB
- references/okf-format.md 3.1 KB
- references/onboarding.json 1.2 KB
- scripts/check_dependencies.py 1.1 KB runs code
- scripts/insert_frontmatter.py 29 KB runs code
- scripts/okf_rules.py 12 KB runs code
- scripts/okf_yaml.py 2.3 KB runs code
- scripts/test_okf.py 35 KB runs code
- scripts/validate_okf.py 4.8 KB runs code
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.
- 9d ago First seen · 29 lines · 115 tokens per session scan A 6933a382f38f
x9-okf-docs is a skill published in the GitHub repository xonika9/agent-skills (4 stars, last pushed 4d ago), licensed MIT. It adds 115 tokens to every session and 447 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
architecture-decision-records
Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.
agent-framework-azure-ai-py
Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
api-security
Authorized security assessment of REST, GraphQL, WebSocket, and SOAP APIs: discovery, authentication and authorization flaws (BOLA/IDOR, JWT/OAuth), rate-limit testing, and a structured multi-phase methodology.
aria
Designs the data model, API contracts, and structural foundation of the system.