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 agentmods add skills/hamakyo/okf-skills/implement-featurenpx skills add hamakyo/okf-skills --skill implement-featuregit 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/implement-feature)<a href="https://agentmods.dev/skills/hamakyo/okf-skills/implement-feature"><img src="https://agentmods.dev/badge/skills/hamakyo/okf-skills/implement-feature.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00652 |
| Opus 5 | $0.00025 | $0.00326 |
| Sonnet 5 | $0.00010 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
implement-feature 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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Feature
When to use
Use this Skill when the task requires:
- Adding a new user-facing or developer-facing capability.
- Changing existing behavior.
- Extending an integration, workflow, UI, API, or data flow.
- Implementing a documented requirement from OKF, an issue, or a user request.
Do not use this Skill for:
- Investigating an unclear bug before root cause is known.
- Adding tests without implementation changes.
- Refactoring that should preserve behavior.
- Updating OKF after code has already changed.
Inputs
- User request or issue description.
- Target repository and branch context.
- Relevant OKF documents, if present.
- Expected validation command or test scope, if known.
Required context
Before editing, read:
README.mdAGENTS.mdorCLAUDE.md, depending on the tool in useokf/index.md- Relevant OKF documents under
okf/architecture/,okf/domain/,okf/data/,okf/features/, orokf/playbooks/ - Existing code and tests around the target behavior
Read okf/log.md only when change history is relevant to the requested behavior.
Workflow
- Restate the requested behavior in concrete terms.
- Identify relevant OKF knowledge and note any gaps or conflicts.
- Inspect the existing implementation path before proposing changes.
- Choose the smallest coherent implementation approach that matches local patterns.
- Make focused code changes.
- Add or update tests when behavior changes.
- Run the narrowest useful verification first, then broader checks when risk warrants it.
- If durable behavior, architecture, data, domain, or playbook knowledge changed, run or recommend the
update-okfSkill.
Guardrails
- Do not skip OKF review when an
okf/directory exists. - Do not invent architecture that conflicts with OKF or existing code.
- Do not broaden the scope into unrelated cleanup.
- Do not silently change public APIs, schemas, migrations, or user-visible behavior beyond the request.
- Do not add secrets, credentials, private URLs, or personal data.
- If requirements are ambiguous and local context cannot resolve them, state the assumption before implementing.
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.
- 4d ago First seen · 81 lines · 50 tokens per session scan A 31ac435a0285
implement-feature is a skill published in the GitHub repository hamakyo/okf-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 50 tokens to every session and 652 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.
Other skills, from other repositories
README Structure
A solid default README shape (what it is, quickstart, key commands, where to find more) and guidance on when a project has outgrown a single README.
EU AI Act Documentation
What compliance documentation to produce under the EU AI Act — Annex IV technical documentation, EU declaration of conformity, risk-management file, data-governance records, and GPAI training-data summary — and how to structure it.
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.
Documentation Standards
Structure, tone, and formatting conventions for writing technical docs that stay accurate and get actually read.
Agent Instruction Drift Check
Procedure for comparing an agent-facing instruction doc (AGENTS.md/CLAUDE.md-style) against the actual current code and configuration to find and flag mismatches.
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.