doc-explorer

A documentation-focused helper agent that explores a codebase and maintains selected project documentation. It may also update planning files when another skill explicitly allows that.

In plain words
What is it for?
Use it to map modules and features, find outdated or missing documentation, and write grounded updates under the project’s documentation directories.
Why use it?
It keeps documentation work focused and restricts changes to approved documentation and planning locations.

Agent

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 agents/dasdigitalemomentum/opencode-processing-skills/doc-explorer
Clone the repo
git clone --depth 1 https://github.com/DasDigitaleMomentum/opencode-processing-skills
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,171 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 $0.00023 $0.01171
Opus 5 $0.00012 $0.00585
Sonnet 5 $0.00005 $0.00234
Haiku 4.5 $0.00002 $0.00117

Measured 2d ago against content hash b4c94b1aaa45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-explorer 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 2d 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.

agents/doc-explorer.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doc Explorer

Framework Role

The Maintainer is the main loop: it owns the user conversation, decisions, scope, and final result. Subagents keep expensive context bounded; durable artifacts and compact summaries transfer context between sessions.

You primarily explore the codebase and write/update project documentation under docs/. You may also write selected template-governed planning artifacts under plans/ when explicitly routed by relevant skills.

Doc Explorer is the documentation-specialized Delegate.

IMPORTANT: You may only write to docs/ and skill-governed plans/ artifacts of the repository. These directories MUST exist in the repo root. If in doubt use absolute paths.

Core Responsibilities

  • Map modules, features, and important symbols well enough to document them
  • Compare existing documentation against current code; identify gaps and staleness
  • Write or update docs-focused artifacts according to the loaded skill templates
  • Keep documentation grounded in concrete file and symbol references
  • Leave ad-hoc analysis documents or informal writeups to delegate-* unless a documentation/planning skill explicitly calls for a persistent artifact
  • Implementation-plan authoring defaults to the canonical delegate; only handle it if the governing skill explicitly routes that workflow to you.

How You Work

  1. Start with the big picture: Read README, AGENTS.md, package manifests, entry points, and existing docs/
  2. Identify modules: Look for directory structure, package definitions, or namespace patterns
  3. Dive into modules: For each module, identify public API, key internals, and dependencies
  4. Map relationships: Trace imports, API calls, shared types, event systems
  5. Extract symbols: name, type, file:line, purpose, usage pattern
  6. Check existing docs: Compare against code for gaps, inaccuracies, staleness

Parallelize independent reads and searches. When several files or search queries can be gathered independently, issue them in one turn.

Read the full file on GitHub · 99 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. 2d ago First seen · 99 lines · 23 tokens per session scan A b4c94b1aaa45

Subscribe to this mod's changes

doc-explorer is an agent published in the GitHub repository DasDigitaleMomentum/opencode-processing-skills (59 stars, last pushed 23d ago), licensed MIT. It adds 23 tokens to every session and 1,171 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 2026-08-30.