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 saulmcphd/okf-skills --skill okf-write-playbookgit clone --depth 1 https://github.com/saulmcphd/okf-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/saulmcphd/okf-skills/okf-write-playbook)<a href="https://agentmods.dev/skills/saulmcphd/okf-skills/okf-write-playbook"><img src="https://agentmods.dev/badge/skills/saulmcphd/okf-skills/okf-write-playbook/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/saulmcphd/okf-skills/okf-write-playbook"><img src="https://agentmods.dev/badge/skills/saulmcphd/okf-skills/okf-write-playbook.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 | $0.00191 | $0.01663 |
| Opus 5 | $0.00096 | $0.00831 |
| Sonnet 5 | $0.00038 | $0.00333 |
| Haiku 4.5 | $0.00019 | $0.00166 |
Grade A, and why
okf-write-playbook 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 10d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Author an OKF playbook node
A playbook is the procedure layer of an OKF bundle: a reproducible, actionable runbook for one stage of the work. A concept holds the knowledge (definitions, rules, thresholds); a playbook says what to do, in order, and links the concepts that justify each rule. This skill is domain-agnostic.
If the repo has an
okf-gold-standard.md, follow its project-specific extensions. This skill is the self-contained baseline. (Note: a bundle can be knowledge-only — playbooks are added when there's a repeatable procedure worth capturing.)
Filename & identity
- Path:
playbooks/playbook-<slug>.md(e.g.playbooks/playbook-spring-bed-prep.md). - The file path is the node id. No
idfield, nolinks:array.
How to build the # Steps — fuse two sources
Build the procedure by fusing two inputs:
- The operational step sequence from the authoring skill/tool for this stage — lift and adapt it to this bundle; don't re-derive it.
- The concept knowledge — each step links the concept(s) that justify its rule/threshold.
Select the relevant concepts by reading index.md (curated navigation). Where a skill step and a
concept conflict, the concept wins (it's grounded in the primary standard) — and you note it.
Mental model: a triage runbook — when this fires → do this → how to weigh it → guardrails.
Frontmatter (YAML)
The standard concept keys plus procedure-specific, queryable fields:
---
type: playbook
title: "Human-readable stage title"
description: "One sentence an agent uses (via index.md) to decide if THIS procedure is the one it needs."
resource: "https://… # canonical source for the procedure, if any"
tags: [stage-tag, domain-tag]
generated: { by: session-authored, at: 2026-07-11T00:00:00Z } # OKF v0.2: replaces timestamp
stage: bed-prep # short stage key
stage_number: "1" # optional ordering within a pipeline
status: built # draft | built | deprecated
provider_agnostic: true # true if it doesn't hard-depend on one vendor/tool
uses_skills: [] # authoring skills this stage runs
scripts: [] # scripts/tools that perform it
inputs: [garden-plan.md] # what it consumes
outputs: [this-season-layout.md] # the artefacts it writes
provenance:
ai_model: claude-opus-4-8
ai_provider: anthropic
prompt_file: session-authored
prompt_version: v1
human_verified: false
---
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.
- 10d ago First seen · 146 lines · 191 tokens per session scan A 0eaac52f733d
okf-write-playbook is a skill published in the GitHub repository saulmcphd/okf-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 191 tokens to every session and 1,663 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…