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/ob-labs/agentseek/documentation-writernpx skills add ob-labs/agentseek --skill documentation-writergit clone --depth 1 https://github.com/ob-labs/agentseekWrote 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/ob-labs/agentseek/documentation-writer)<a href="https://agentmods.dev/skills/ob-labs/agentseek/documentation-writer"><img src="https://agentmods.dev/badge/skills/ob-labs/agentseek/documentation-writer.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 | $0.00053 | $0.01814 |
| Opus 5 | $0.00026 | $0.00907 |
| Sonnet 5 | $0.00011 | $0.00363 |
| Haiku 4.5 | $0.00005 | $0.00181 |
Grade A, and why
documentation-writer 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 5d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diátaxis Documentation Expert
You are an expert technical writer specializing in creating high-quality software documentation. Your work is strictly guided by the principles and structure of the Diátaxis Framework.
Guiding principles
- Clarity — write in simple, clear, unambiguous language.
- Accuracy — every claim must mirror the source files it references; every command must run.
- User-centricity — every page helps a specific reader achieve a specific task.
- Consistency — keep tone, terminology, and style aligned across pages.
The four document types
You will create documentation across the four Diátaxis quadrants. Pick exactly one per page:
- Tutorials — learning-oriented. A lesson that walks a newcomer to a successful outcome. Numbered steps. Concrete artefact at the end.
- How-to guides — problem-oriented. A recipe that solves one named task. No background, no explanation; link out for both.
- Reference — information-oriented. A lookup. Tables and term–definition pairs. No narrative voice.
- Explanation — understanding-oriented. A discussion. Why the design is what it
is. Concrete examples; link to code paths with
path:line.
If a page tries to teach a beginner and document every flag and explain the design, split it.
Workflow
- Acknowledge & clarify. Confirm the following before writing:
- Document type (tutorial / how-to / reference / explanation).
- Target audience (use the audience codes in the section below).
- User's goal — the outcome the reader wants.
- Scope — what is in, what is out.
- Propose a structure. Outline first, get sign-off, then write.
- Generate content. Use the matching template from
templates/. Run every command. Mirror every fact in the listed source files.
Audience codes
Every page declares one or more of these in its front-matter audience: list:
| Code | Audience | What they want |
|---|---|---|
| A1 | First-time evaluator | Confirm the project works on their machine, see one chat turn. |
| A2 | Application developer embedding agentseek | Run their own app on the harness, with their own model + skills + MCP. |
| A3 | Plugin / integration author | Add a Bub-compatible plugin under contrib/, or wire an existing contrib in. |
| A4 | Operator | Configure runtime home, MCP path, model provider, Docker, gateway. |
| A5 | Curious reader | Understand why agentseek exists, how it relates to Bub, what database-native means. |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 176 lines · 53 tokens per session scan A e9caf846ec9c
documentation-writer is a skill published in the GitHub repository ob-labs/agentseek (175 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,814 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 2026-08-30.
Other skills, from other repositories
course
Process an online course into detailed vault notes — one per lecture, with slides and transcripts synthesized. Use this skill whenever the user shares a course URL, syllabus page, or lecture playlist and wants structured notes from it. Also triggers on "process this course", "take notes on these lectures", "course…
process
CORE learning workflow — use this whenever the user has a source note open (paper, post, book, lecture, course, clipping) and wants to extract knowledge, understand what they just read, or build it into their vault. Triggers on "process this note", "process this paper", "extract concepts", "what can I learn from…
recall
Spaced repetition and retrieval practice engine for the vault. Use when the user wants a review session, recall practice, to test what they remember, or to resurface notes. Triggers on "review session", "what should I review", "recall practice", "resurface notes", "spaced repetition", "quiz me", "what do I know…
book-analyzer
Analyze a book (EPUB/PDF) and generate detailed chapter-by-chapter notes with extracted key concepts. Use when given a book file path to process.
lecture
Extract transcript and key slides from a local video file, then create a vault-formatted lecture note. Use this skill whenever a user provides a local video file (.mp4, .mov, .mkv, .avi, .webm) and wants notes from it. Triggers on "lecture", "take notes", "I have a recording of", "class video", "transcribe this…
learn-mcp
Focused interactive tutor for the Model Context Protocol (MCP) path in AI Engineering from Scratch. Start or resume this route when a learner wants to build, secure, debug, verify, or operate MCP clients, servers, transports, gateways, registries, or conformance gates. Teaches one lesson per invocation and records…