dw-init

dw-init is a skill for Claude Code from dominikwozniak/dw-solo-skills. It costs 78 tokens per session (5,138 once invoked), scanned A, original, MIT.

A repository setup workflow for a solo coding process. It creates folders and documents for active changes, follow-ups, archived work, project decisions, project terms, instructions, and verification steps.

In plain words
What is it for?
Use it to prepare a repository with tracked .ai folders, decision records, a glossary, AGENTS.md instructions, a verification guide, guardrail hooks, and related settings.
Why use it?
It gives the coding workflow a consistent place to store task state, project knowledge, rules, and safety checks.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Good fit Use it to prepare a repository with tracked .ai folders, decision records, a glossary, AGENTS.md instructions, a verification guide, guardrail hooks, and related settings.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote 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.

agentmods badge for dw-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/dominikwozniak/dw-solo-skills/dw-init/github.svg)](https://agentmods.dev/skills/dominikwozniak/dw-solo-skills/dw-init)
Your own site
<a href="https://agentmods.dev/skills/dominikwozniak/dw-solo-skills/dw-init"><img src="https://agentmods.dev/badge/skills/dominikwozniak/dw-solo-skills/dw-init/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dw-init

Your own site · 80×15
<a href="https://agentmods.dev/skills/dominikwozniak/dw-solo-skills/dw-init"><img src="https://agentmods.dev/badge/skills/dominikwozniak/dw-solo-skills/dw-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,138 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00078 $0.05138
Opus 5 $0.00039 $0.02569
Sonnet 5 $0.00016 $0.01028
Haiku 4.5 $0.00008 $0.00514

Measured 3d ago against content hash 5bb1426b4082, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dw-init 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 3d 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.

skills/dw-init/SKILL.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dw-init — scaffold a repo for the solo lane

Everything the loop assumes a repo has, written in one gated pass: the .ai/ state the skills read and write, the durable homes they promote into, the guardrail hooks, and a settings file whose allow-list is derived from the project rather than guessed.

What it writes

Path Tracked? Purpose
.ai/work/ tracked one folder per change (dw-shape writes CHANGE.md)
.ai/README.md tracked what .ai/ is and who owns it
.ai/backlog/ + its README.md tracked one file per follow-up, between changes
.ai/archive/ + its README.md tracked landed change docs — history, not guidance
docs/decisions/ + its README.md tracked durable decision records (dw-land promotes here)
CONTEXT.md tracked the project's glossary — terms only
VERIFY.md tracked how to start this project and drive a feature by hand
AGENTS.md tracked the one always-loaded file: rules, commands, Task Router
CLAUDE.md tracked a symlink to AGENTS.md — never a second copy
scripts/check-agents-docs.mjs tracked the gate on that file's budget, router and commands
.claude/settings.json tracked permissions (ask + deny + derived allow) and hook wiring
.claude/hooks/*.sh tracked the guardrail scripts those settings reference
.worktreeinclude tracked gitignored files a fresh worktree should carry in
.github/PULL_REQUEST_TEMPLATE.md tracked the PR body shape dw-land fills and GitHub prefills
.gitignore tracked a managed marker block for the personal files
.husky/ + .lintstagedrc.json tracked, optional the pre-commit twin of the hooks — only when opted in

Read the full file on GitHub · 273 lines

Files

What ships with it

1 file 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.

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. 3d ago Changed · +4 lines 5bb1426b4082
  2. 7d ago Changed · +12 lines 61fa3bd0eb3f
  3. 12d ago First seen · 257 lines · 78 tokens per session scan A 9b73c6da7acb

Subscribe to this mod's changes

dw-init is a skill published in the GitHub repository dominikwozniak/dw-solo-skills (2 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 5,138 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

setup-working-genius

Per-repo configuration — pin the work-file directory, verify commands, and issue tracking, seed the project docs, and leave the pointer that tells every future session this project works this way.

donald-ada/workinggenius · 43 tokens

daily-working

End-to-end pipeline: pull a task from the project's task tracker by ID (Redmine or GitHub Issues today, more addable via a new adapter), sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension…

tms-tungnguyen3/daily_working · 98 tokens

compact

Put the compaction question to a snapshot that drifted — route what no longer constrains unfinished work, and say what moves before moving it. In flight or done; the log is appended to, never edited or trimmed.

donald-ada/workinggenius · 47 tokens

genius

The map of the Working Genius workflow — where each piece of work stands, what to run next, and where genius gaps are hiding.

donald-ada/workinggenius · 30 tokens

work

Dispatch a tracker ticket into an isolated worktree and drive it autonomously to an open pull request, then stop for review. Pass interactive to brainstorm the ticket with a human before planning it, or a sentence of editorial direction as a rider. Use when asked to work a ticket end-to-end.

mikestankavich/claude-ship-workflow · 0 tokens

batch

Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.

mikestankavich/claude-ship-workflow · 31 tokens