add-docs

A command that researches a library or framework's full documentation website and creates a system prompt for qdoc's agent, a tool that works with documentation.

In plain words
What is it for?
It helps build a documentation-aware agent for a specified library or framework and connects that agent's generated prompt to the codebase.
Why use it?
It removes the need to map the documentation site and summarize its sections manually, including guides, API references, troubleshooting pages, migration notes, and versioned content.

Command

Install

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.

agentmods
npx agentmods add commands/ibrhr/qdoc/add-docs
Clone the repo
git clone --depth 1 https://github.com/ibrhr/qdoc
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,297 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.01297
Opus 5 $0.00014 $0.00648
Sonnet 5 $0.00005 $0.00259
Haiku 4.5 $0.00003 $0.00130

Measured yesterday against content hash 37de80f18624, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-docs 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 yesterday.

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.

.opencode/commands/add-docs.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research the $ARGUMENTS documentation site thoroughly. This is a multi-phase task. Complete each phase before moving to the next.

Phase 1: Discover the documentation site

Search the web to find the official documentation URL for $ARGUMENTS. Once found:

  • Note the base URL (e.g. https://docs.example.com)
  • Note the index page URL (the page listing all doc pages — usually the root or /docs)
  • Note any link prefix that filters to doc-only pages (e.g. /docs/, /latest/)

Confirm the URL is accessible by fetching it.

Phase 2: Traverse and map the documentation

Fetch the index page and study ALL available documentation pages. Your goal is to understand where every piece of information lives. Specifically:

  1. Categories of docs (getting-started, guides, API reference, tutorials, advanced, deployment, etc.)
  2. Sub-paths under each category and what they cover
  3. Hidden/less-obvious sections (changelogs, migration guides, internal architecture, community pages, contributing guides, security policies, deprecation notices)
  4. Special pages (glossary, FAQ, troubleshooting, common-errors, best-practices, style-guide)
  5. Version-specific pages (e.g. /v2/, /v3/, /next/)
  6. How the docs differentiate between major versions or editions (e.g. App Router vs Pages Router in Next.js, or Standard Library vs Language Reference in Python)
  7. Non-obvious docs: CLI references, configuration file options, environment variables, editor/IDE setup, testing guides, benchmarking, deployment checklists

Be thorough. Read 5-10 actual pages to understand the content depth and style. Note:

  • How deeply nested sections go
  • Whether pages are self-contained or reference each other heavily
  • Whether examples are runnable or illustrative
  • Whether there are interactive playgrounds or sandboxes

Phase 3: Analyze and take notes

Study the documentation structure thoroughly in your working context (no persisted file). Note:

  • The full categorized layout of sections and sub-paths
  • Hidden/non-obvious sections (changelogs, migration guides, security policies, deprecation notices, contributing guides, glossary, FAQ)
  • Quirks & gotchas (URL overlaps, deprecated pages still indexed, redirects, sparse pages, JS-rendered content)
  • Content quality: shallow vs deep coverage, example quality, cross-referencing habits

Read the full file on GitHub · 109 lines

Changes

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.

  1. yesterday First seen · 109 lines · 27 tokens per session scan A 37de80f18624

Subscribe to this mod's changes

add-docs is a command published in the GitHub repository ibrhr/qdoc (2 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 1,297 once invoked, about $0.0001 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.