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 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/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/ob-labs/agentseek/documentation-writer"><img src="https://agentmods.dev/badge/skills/ob-labs/agentseek/documentation-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.01814 |
| Opus 5.5 | $0.00021 | $0.00726 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo 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 (201 stars, last pushed 13d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,814 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 2026-08-30.
Other skills, from other repositories
first-reader
Beta readers for any draft, run by simulating how a real reader experiences it, moment by moment. A skim gate, a no-lookahead timed read producing an attention transcript with quit points, a recall test of what a reader remembers the next day, and a trust ledger of the implied author. Use when the user asks for a beta…
mcp-apps-builder
MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: Creating new MCP servers Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) Debugging MCP server issues or errors Reviewing MCP server code for…
project-graveyard
Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…
commit-archaeologist
Reconstructs why code exists from local git history, including the introducing commit, later changes, current authors, repeated companion files, and likely intent. Use when the user asks "why does this code exist", "who wrote this function and why", or to "explain the history of this function" before a rewrite…
dependency-doctor
Checks requirements.txt, pyproject.toml, and package.json dependency manifests for surface-level direct-dependency footguns: standard-library shadowing pins, abandoned backports, unpinned dependencies, and obvious intra-manifest conflicts, plus opt-in PyPI yanked releases. Use when the user asks to check a manifest…
scope-creep-detector
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too…