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 hamakyo/okf-skills --skill update-okfgit clone --depth 1 https://github.com/hamakyo/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/hamakyo/okf-skills/update-okf)<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.
<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>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 | $0.00058 | $0.00882 |
| Opus 5.5 | $0.00023 | $0.00353 |
| Sonnet 5.5 | $0.00012 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
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 1mo 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 — 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 diffor a list of changed files. - Relevant issue, PR, or user request.
- Existing OKF bundle.
- Date for
okf/log.mdentry. - Current producer actor in OKF form when known, such as
tool/version,human:<id>, orprocess:<id>.
Required context
Before editing OKF, read:
okf/index.mdokf/log.md- Existing OKF documents related to changed behavior
- The implementation diff
- README or docs when the public usage story changed
Workflow
- Inspect
git diffor changed files. - 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.
- Map each knowledge change to an existing OKF document or create a new concept document.
- Add or update YAML frontmatter for non-reserved concept documents:
- Keep
typenon-empty. - Add or update
sourceswhen identifiable source material changed. - When
generatedexists and content meaningfully changes, updategenerated.byandgenerated.atfor the current producer. - Add
generatedwhen the producer is known and can be represented without guessing. - Remove or replace
verifiedevents after meaningful content changes unless the new content was verified again. - Set
statusonly whendraftordeprecatedconveys useful lifecycle information; omission meansstable. - Set
stale_afteronly when an absolute validity horizon is known. - Do not add the legacy
timestampfield.
- Keep
- Keep
okf/index.mdaccurate when adding, moving, or removing OKF documents. - Add a dated entry to
okf/log.mdusingYYYY-MM-DD. - Avoid copying large code blocks unless they are the best durable reference.
- Verify Markdown links and YAML metadata.
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.
- 1mo ago First seen · 98 lines · 58 tokens per session scan A 98aa2e1503ea
update-okf is a skill published in the GitHub repository hamakyo/okf-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 882 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
Memory System
Maintain a tiered, file-based memory system so project context and decisions survive across sessions instead of being rediscovered or contradicted each time.
session-flow
Reorient in the current Claude Code session with an evidence-backed map of its goal, pivots, outcomes, current step, and open decisions.
wiki
LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model).
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
context-exclusion
Maintain .agent-no-read.md markers for approved generated directories using deterministic scripts. Use when configuring generated-code context exclusion or restoring markers after regeneration, not for ordinary ignore rules or OS permissions.
context-lifecycle
Author, review, or integrate Agent Context Lifecycle Protocol V1 declarations and adapters. Use for explicit ephemeral messages, persistent named blocks, trusted discard controls, or agent compatibility questions; do not claim Codex itself can rewrite prior request history.