Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Summary

Generate wiki docs + detect documentation drift for Claude Code

Install to Claude Code

/plugin install driftwiki@driftwiki-marketplace

Run in Claude Code. Add the marketplace first with /plugin marketplace add dpviivqb/driftwiki if you haven't already.

README.md

driftwiki

driftwiki = deepwiki-skill (wiki generation) + a drift detection layer (new). A Claude Code agent skill that both generates wiki docs and detects drift between docs and code.

> Forked from deepwiki-skill (MIT), adding Phase 7 drift-check to its 6-phase generation workflow.

Why (deepwiki-skill's gaps + our patch)

deepwiki-skill generates good docs, but two hard gaps:

  • It only generates, never detects drift — docs go stale after generation, it doesn't notice.
  • Its citations can hallucinate — even its own self-generated docs have line numbers that don't match the code.

driftwiki adds the detection layer:

  • Endpoint driftast-extract FastAPI endpoints vs doc endpoint tables; report missing / extra (each with file:line).
  • Citation line check — validate GitHub blob#L<line> refs in docs; file exists + line in range (catches hallucination).

Install

/plugin marketplace add https://github.com/dpviivqb/driftwiki
/plugin install driftwiki@driftwiki-marketplace

Usage

/driftwiki:gen                     # generate wiki (inherited from deepwiki-skill)
/driftwiki:check                   # detect doc/code drift (driftwiki's addition)
/driftwiki:check --output docs/drift-report.md
/driftwiki:check --docs README.md,docs/api.md

/driftwiki:check runs scripts/drift_check.py, auto-discovering FastAPI endpoints and all .md docs in the repo, then emits a drift report (Markdown + JSON).

Real example (on this repo)

Repo: .../job_outreach  Code endpoints: 18 (prefix /api/v1)
REPOWIKI.md: Doc endpoints 15 | Missing 3 | Extra 0
  Missing (in code, not in doc):
    GET /extension-auth/diagnostics  <- routers/extension_auth.py:56
    GET /orders/list                 <- routers/orders.py:33
    POST /auth/access-token          <- routers/auth.py:77
docs/wiki/07_backend-api.md: Doc 18 | Missing 0 | Extra 0
Citation check: 25 citations, 0 anomalous

Catches 3 endpoints that the repowiki-generated REPOWIKI missed. This is what deepwiki-skill / repowiki do not do.

Relationship to deepwiki-skill

  • Forked from natsu1211/deepwiki-skill (MIT).
  • Keeps all its generation power (repo-scan -> toc-design -> doc-write -> validate-docs -> doc-summary -> incremental-sync).
  • Adds Phase 7 drift-check + scripts/drift_check.py + commands/check.md.
  • Thanks to upstream.

Constraints

  • Generation (inherited from deepwiki-skill) may hang in headless mode in some environments (a subagent-spawn issue). Drift detection (added) is a pure-Python stdlib script, stable.
  • MVP detection: FastAPI endpoint drift + citation line check. Future: more frameworks (Express / Django / Spring) and detection types (model fields, pricing).

License

MIT (inherited from deepwiki-skill).

Related plugins

Browse all →