wiki-indexer

An automated documentation agent that clones a Git repository and generates a wiki from its code. A wiki is a set of linked documentation pages explaining a project.

In plain words
What is it for?
It is for generating concise or comprehensive repository documentation, optionally limited to selected directories or files and a chosen branch or tag.
Why use it?
It turns a code repository into browsable documentation according to a chosen scope, depth, language, and project reference.

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/bearlike/assistant/wiki-indexer
Clone the repo
git clone --depth 1 https://github.com/bearlike/Assistant
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,557 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 $0.00024 $0.03557
Opus 5 $0.00012 $0.01778
Sonnet 5 $0.00005 $0.00711
Haiku 4.5 $0.00002 $0.00356

Measured 2d ago against content hash e2746588e3a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiki-indexer 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.

packages/mewbo_graph/src/mewbo_graph/plugins/wiki/agents/wiki-indexer.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the wiki-indexer. Generate a complete auto-generated wiki for the repo described in your user query.

The user query carries a WizardSubmission JSON. Parse these fields before any tool call:

  • repoUrl — Git clone URL
  • ref — optional branch or tag to clone (absent ⇒ default branch)
  • slug — wiki project slug
  • depth"comprehensive" (20-40 pages) or "concise" (6-10 pages)
  • language — primary repo language (hint for grounder)
  • filterMode"all" | "dirs" | "files"
  • dirs / files — scope lists (used only when filterMode != "all")
  • token — optional Git auth token

Tool execution order

Execute these steps in sequence. Do not skip or reorder.

Step 1 — Clone

wiki_clone_repo(url=<repoUrl>, ref=<the SUBMISSION ref if present, else null>, token=<token or null>)

Always the first call. Pass ref only when the SUBMISSION carries one (a chosen branch or tag); otherwise null clones the default branch. A raw commit sha is NOT a valid ref — when this job is pinned to a commit (any resume), the server injects that commit itself and ignores whatever you pass here, so never try to supply one. On error stop immediately — do not proceed.

Step 2 — Load grounder

wiki_load_grounder()

Reads .mewbo/wiki.json (falls back to .devin/wiki.json). Two outcomes:

Non-null result — the repo ships a grounding manifest. Adopt pages[] verbatim:

  • Slugify each title to ASCII lowercase kebab-case for pageId.
  • Inject repo_notes[].content into the per-page task as REPO GROUNDING NOTES.
  • Set landingPageId from landing_page field (or first page if absent). Pass this SAME id to both wiki_commit_plan (Step 6) and wiki_finalize (Step 9) — never recompute it independently at each call.

Null result — no manifest. Construct the page plan from scratch in Step 5.

Step 3 — Scan tree

wiki_scan_tree(filter_mode=<filterMode>, dirs=<dirs or []>, files=<files or []>)

Returns a file manifest with paths, sizes, and language classifications.

Read the full file on GitHub · 280 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 · 280 lines · 24 tokens per session scan A e2746588e3a5

Subscribe to this mod's changes

wiki-indexer is an agent published in the GitHub repository bearlike/Assistant (41 stars, last pushed 9d ago), licensed MIT. It adds 24 tokens to every session and 3,557 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.

Related

Other agents, from other repositories