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/aiocean/claude-plugins/aio-doc-writernpx skills add aiocean/claude-plugins --skill aio-doc-writergit clone --depth 1 https://github.com/aiocean/claude-pluginsWrote 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/aiocean/claude-plugins/aio-doc-writer)<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-doc-writer"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-doc-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 5.1 | $0.00038 | $0.04990 |
| Opus 5 | $0.00019 | $0.02495 |
| Sonnet 5 | $0.00008 | $0.00998 |
| Haiku 4.5 | $0.00004 | $0.00499 |
Grade A, and why
aio-doc-writer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Oracle
SCRIPTS="${CLAUDE_PLUGIN_ROOT}/skills/aio-doc-writer/scripts"
Environment
- GitNexus: !
npx gitnexus status 2>/dev/null && echo "AVAILABLE" || echo "NOT INSTALLED"
Comprehensive architecture documentation powered by GitNexus knowledge graph combined with Oracle direct documentation writing and LSP precision analysis.
Core Philosophy: Oracle writes all documentation from scratch using GitNexus's knowledge graph (structure, dependencies, clusters, flows, hybrid search) combined with LSP type-aware analysis and direct source code reading.
What GitNexus Provides: A precomputed knowledge graph — nodes (functions, classes, modules), edges (imports, calls, inheritance), clusters (functional communities with cohesion scores), execution flows from entry points, and hybrid search (BM25 + semantic). All from a single npx gitnexus analyze.
What LSP Provides: Type-aware precision — hover info, exact reference counts, caller tracing, diagnostics, rename safety.
What Oracle Provides: All written documentation — module docs, architecture analysis, key flows, dependency narratives, failure modes, design rationale, and decision guidance.
Documentation Intent Contract
Before writing or updating any docs, declare this contract:
- Audience: Who will use this doc (
new engineer,oncall,feature owner,refactor owner). - Primary tasks: Top 2-3 questions the reader should answer quickly.
- Decision horizon: What decisions this doc supports (incident, refactor, onboarding, architecture review).
- Out of scope: What this doc intentionally does not cover.
If user does not specify, infer from context and state assumptions explicitly in CODEBASE_MAP.md.
Evidence and Confidence Protocol
Every non-trivial claim must be represented as:
Claim- factual statement.Evidence- one or morepath:linereferences.Confidence-░░░░░to▓▓▓▓▓.Impact- why this matters to decisions.
What ships with it
25 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.
- graph.html.tpl 45 KB
- references/architecture-analysis.md 21 KB
- references/quality-gates.md 2.3 KB
- references/tools-integration.md 5.9 KB
- references/writing-quality.md 12 KB
- scripts/doc-quality-check.sh 5.9 KB runs code
- scripts/scan-codebase.py 15 KB runs code
- scripts/tree-sitter-analyze.py 29 KB runs code
- templates/adr.md.tpl 5.5 KB
- templates/api-surface.md.tpl 3.8 KB
- templates/architecture.md.tpl 5.8 KB
- templates/CODEBASE_MAP.md.tpl 3.9 KB
- templates/component.md.tpl 3.1 KB
- templates/data-model.md.tpl 3.0 KB
- templates/dependencies.md.tpl 7.1 KB
- templates/infrastructure.md.tpl 3.5 KB
- templates/key-flows.md.tpl 2.8 KB
- templates/module.md.tpl 2.6 KB
- templates/observability.md.tpl 7.1 KB
- templates/onboarding.md.tpl 7.2 KB
- templates/overview.md.tpl 3.5 KB
- templates/product-requirements.md.tpl 2.8 KB
- templates/quality.md.tpl 3.7 KB
- templates/security.md.tpl 8.2 KB
- templates/testing.md.tpl 6.2 KB
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 · 466 lines · 38 tokens per session scan A 7459fd4e7571
aio-doc-writer is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 4,990 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 2026-08-31.
Other skills, from other repositories
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.
investigate
Systematic root-cause debugging: find the cause before writing any fix.
sandbox-unblock
Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eight checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…
source-command-methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
canary
Post-deploy monitoring: watch production after a deploy and alert on regressions.