Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.agents/skills/write-okf-markdown/SKILL.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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/bredmond1019/claude-sdk-rs/write-okf-markdown)<a href="https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/write-okf-markdown"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/write-okf-markdown/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/bredmond1019/claude-sdk-rs/write-okf-markdown"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/write-okf-markdown.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 | $0.00180 | $0.04032 |
| Opus 5.5 | $0.00072 | $0.01613 |
| Sonnet 5.5 | $0.00036 | $0.00806 |
| Haiku 4.5 | $0.00018 | $0.00403 |
Grade A, and why
write-okf-markdown 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 11d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing markdown in this brain
Paths below are relative to the brain root — the directory containing
brain.toml, found by walking up from wherever you are. This skill is synced into every repo, so a repo-relative link would be wrong in most of them.
Three separate obligations, in this order. Most breakages come from doing #1 and skipping #2.
- Frontmatter — if the file is a corpus member (Step 1 decides).
- An
index.mdrow — Standing Rule 7. Skipping this is the most common failure. - Validation — one flag per invocation; they do not compose.
The schema tables (every field, every controlled vocabulary, per-type examples) live in
docs/okf-frontmatter.md, governed by docs/decisions/D27-enriched-okf-frontmatter.md. This skill is the procedure, not the
schema — read that doc when you need to pick a type, a layer, or a status.
Step 1 — Does this file need frontmatter at all?
Deterministic, from core/mev/src/brain/crawl.rs::is_corpus_member. A file is a corpus member iff,
relative to its owning repo root, it is:
- exactly
README.md,CLAUDE.md, orindex.mdat the repo root, or - anywhere under
planning/ordocs/(any depth).
Those three filenames are matched literally.
GEMINI.mdandAGENT.mdsit besideCLAUDE.mdat the same repo roots and are not corpus members — they carry no frontmatter obligation and no index row, and editing one changes nothing a gate can see. Do not "correct"CLAUDE.mdto another agent's filename anywhere in this document; the rule is the string, not the tool.
Everything else — src/*.md, a stray root-level .md, anything under an unregistered directory — is
out of corpus: no frontmatter obligation, no index row, no validation.
Then subtract the ephemeral names, from crawl.rs::is_ephemeral. These are excluded even inside
planning/:
handoff.md · tasks.md · breakdown.md · worklog.md · any filename starting with _
The
_prefix is a debugging trap, not just a convention. A probe named_zz_test.mdis invisible tovalidate-brain. You will conclude detection is broken when it is working exactly as designed. If you are testing whether a check fires, do not name the fixture with a leading_.
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.
- 11d ago First seen · 294 lines · 180 tokens per session scan A 7b21aa295a24
write-okf-markdown is a skill published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 180 tokens to every session and 4,032 once invoked, about $0.0007 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 2026-10-26.
write-okf-markdown compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| write-okf-markdownbredmond1019/claude-sdk-rs | Skill | 23 | 1mo ago | Apache-2.0 | A | 180 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| ppt-reviewOrkas-AI/Orkas | Skill | 9.0k | today | MIT | A | 2 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |