update-okf

update-okf is a skill for Claude Code from hamakyo/okf-skills. It costs 58 tokens per session (882 once invoked), scanned A, original, MIT.

A workflow for updating the project's durable knowledge documents after code or documentation changes. It records lasting changes to behavior, architecture, terminology, data, or operating procedures in the relevant OKF documents and log.

In plain words
What is it for?
Use it after changes that affect user-visible behavior, module boundaries, business rules, data contracts, migrations, or recurring operational procedures.
Why use it?
It prevents important project knowledge from living only in a code diff or one person's memory. It also avoids recording temporary investigation notes as permanent documentation.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it after changes that affect user-visible behavior, module boundaries, business rules, data contracts, migrations, or recurring operational procedures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hamakyo/okf-skills/update-okf
Install

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.

Any agent
npx skills add hamakyo/okf-skills --skill update-okf
Clone the repo
git clone --depth 1 https://github.com/hamakyo/okf-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for update-okf

README.md
[![agentmods](https://agentmods.dev/badge/skills/hamakyo/okf-skills/update-okf/github.svg)](https://agentmods.dev/skills/hamakyo/okf-skills/update-okf)
Your own site
<a href="https://agentmods.dev/skills/hamakyo/okf-skills/update-okf"><img src="https://agentmods.dev/badge/skills/hamakyo/okf-skills/update-okf/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.

agentmods 80×15 button for update-okf

Your own site · 80×15
<a href="https://agentmods.dev/skills/hamakyo/okf-skills/update-okf"><img src="https://agentmods.dev/badge/skills/hamakyo/okf-skills/update-okf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 882 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00058 $0.00882
Opus 5 $0.00029 $0.00441
Sonnet 5 $0.00012 $0.00176
Haiku 4.5 $0.00006 $0.00088

Measured 9d ago against content hash 98aa2e1503ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

update-okf 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.

examples/claude-code-project/.claude/skills/update-okf/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update OKF

When to use

Use this Skill after code or documentation changes that affect:

  • User-visible behavior.
  • Architecture, ownership, or module boundaries.
  • Domain terminology or business rules.
  • Data structures, schemas, contracts, or migrations.
  • Operational playbooks or recurring procedures.

Do not use this Skill for:

  • Temporary investigation notes.
  • Formatting-only changes.
  • Internal refactors that do not alter durable knowledge.
  • Duplicating implementation details that are already obvious from code and not useful as project knowledge.

Inputs

  • Current git diff or a list of changed files.
  • Relevant issue, PR, or user request.
  • Existing OKF bundle.
  • Date for okf/log.md entry.
  • Current producer actor in OKF form when known, such as tool/version, human:<id>, or process:<id>.

Required context

Before editing OKF, read:

  • okf/index.md
  • okf/log.md
  • Existing OKF documents related to changed behavior
  • The implementation diff
  • README or docs when the public usage story changed

Workflow

  1. Inspect git diff or changed files.
  2. Extract only durable knowledge changes:
    • New or changed behavior.
    • New or changed architecture.
    • New or changed domain terms.
    • New or changed data contracts.
    • New or changed playbooks.
  3. Map each knowledge change to an existing OKF document or create a new concept document.
  4. Add or update YAML frontmatter for non-reserved concept documents:
    • Keep type non-empty.
    • Add or update sources when identifiable source material changed.
    • When generated exists and content meaningfully changes, update generated.by and generated.at for the current producer.
    • Add generated when the producer is known and can be represented without guessing.
    • Remove or replace verified events after meaningful content changes unless the new content was verified again.
    • Set status only when draft or deprecated conveys useful lifecycle information; omission means stable.
    • Set stale_after only when an absolute validity horizon is known.
    • Do not add the legacy timestamp field.
  5. Keep okf/index.md accurate when adding, moving, or removing OKF documents.
  6. Add a dated entry to okf/log.md using YYYY-MM-DD.
  7. Avoid copying large code blocks unless they are the best durable reference.
  8. Verify Markdown links and YAML metadata.

Read the full file on GitHub · 98 lines

Changes

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.

  1. 9d ago First seen · 98 lines · 58 tokens per session scan A 98aa2e1503ea

Subscribe to this mod's changes

update-okf is a skill published in the GitHub repository hamakyo/okf-skills (2 stars, last pushed 19d ago), licensed MIT. It adds 58 tokens to every session and 882 once invoked, about $0.0003 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.