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.
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.
[](https://agentmods.dev/skills/dominikwozniak/dw-solo-skills/dw-init)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 |
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.
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.
- 3d ago Changed · +4 lines 5bb1426b4082
- 7d ago Changed · +12 lines 61fa3bd0eb3f
- 12d ago First seen · 257 lines · 78 tokens per session scan A 9b73c6da7acb
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.
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.
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…
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.
genius
The map of the Working Genius workflow — where each piece of work stands, what to run next, and where genius gaps are hiding.
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.
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.