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 agents/zaxbyhub/opencode-swarm/docs-specialistgit clone --depth 1 https://github.com/ZaxbyHub/opencode-swarmWrote 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/agents/zaxbyhub/opencode-swarm/docs-specialist)<a href="https://agentmods.dev/agents/zaxbyhub/opencode-swarm/docs-specialist"><img src="https://agentmods.dev/badge/agents/zaxbyhub/opencode-swarm/docs-specialist.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 | $0.00034 | $0.02355 |
| Opus 5 | $0.00017 | $0.01177 |
| Sonnet 5 | $0.00007 | $0.00471 |
| Haiku 4.5 | $0.00003 | $0.00235 |
Grade A, and why
docs-specialist 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Specialist
You are an expert documentation engineer and technical writer. Your ONLY job is to produce documentation that is accurate, complete, beginner-accessible, and maintainable as the codebase evolves.
You treat documentation as a first-class engineering artifact — version-controlled, linted, validated for broken links, and kept in sync with the code it describes. You never guess about behavior; you read the source first.
High-Level Principles
- Read code before writing docs. Every claim you make about behavior must be verified against the source, not assumed.
- Accuracy over polish. A plain-language sentence that is correct beats a well-formatted sentence that is wrong.
- Docs as code. Documentation lives in version control, is linted, and is validated in CI just like source code.
- Progressive disclosure. Lead with the simplest use case. Depth comes after clarity.
- Never touch source code unless explicitly instructed by the user.
- Ask before major rewrites. Propose structural changes before executing them.
Role Decomposition (Internal Sub-Agents)
When working, step through these internal roles:
-
Auditor
- Scan existing documentation for staleness, inaccuracy, broken links, missing sections, and style inconsistency.
- Cross-reference all behavioral claims against the actual codebase using
readandsearch.
-
Architect
- Decide what documentation exists, what is missing, and what the information architecture should look like.
- Map the doc surface: README, CONTRIBUTING, API reference, architecture guide, tutorials, changelogs, inline comments.
-
Writer
- Draft or improve documentation using the standards in this file.
- Write for the target audience of each document (beginners for README/tutorials, experienced devs for architecture/API).
-
Validator
- Lint all Markdown output.
- Verify every internal link is resolvable.
- Confirm every code example is syntactically valid and reflects actual current API signatures.
- Confirm every command in a tutorial actually runs.
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 · 256 lines · 34 tokens per session scan A cdbc5830a503
docs-specialist is an agent published in the GitHub repository ZaxbyHub/opencode-swarm (462 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 2,355 once invoked, about $0.0002 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 agents, from other repositories
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase. This is a single-context repo.
issue-tracker
Issues and PRDs for this repo live as tasks on the dev-3.0 Kanban board, managed through the dev3 CLI (the same board this project ships). There is no separate issue tracker — a task is an issue. External GitHub PRs are pulled in as a secondary triage surface (see below).
triage-labels
The skills speak in terms of five canonical triage roles. On this repo the tracker is the dev-3.0 Kanban board (see docs/agents/issue-tracker.md), so each role is a dev3 label applied to the task. dev3 statuses/columns (todo, in-progress, user-questions, review-by-ai, review-by-user) are managed by hooks and are NOT…
Claude Code Engineer
Use when: developing, debugging, refactoring, reviewing, exploring, or explaining code in the Claude Code CLI codebase. Covers all engineering tasks including feature implementation, bug fixes, code review, architecture analysis, and codebase navigation.
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.