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-land)<a href="https://agentmods.dev/skills/dominikwozniak/dw-solo-skills/dw-land"><img src="https://agentmods.dev/badge/skills/dominikwozniak/dw-solo-skills/dw-land/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-land"><img src="https://agentmods.dev/badge/skills/dominikwozniak/dw-solo-skills/dw-land.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 | $0.00074 | $0.02202 |
| Opus 5 | $0.00037 | $0.01101 |
| Sonnet 5 | $0.00015 | $0.00440 |
| Haiku 4.5 | $0.00007 | $0.00220 |
Grade A, and why
dw-land scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dw-land — one thin verdict, then keep what's worth keeping
Two phases, and the gate between them is your word.
What it reads and writes
The diff against the default branch — the ref bash "${CLAUDE_PLUGIN_ROOT}/scripts/base-ref.sh" prints — plus
the branch's .ai/work/<date>-<slug>/CHANGE.md (found by the same grep dw-next uses), CONTEXT.md
and docs/decisions/, so the verdict judges against this project's choices. Writes the closing
checklist's targets, moves the change doc to .ai/archive/, then pushes and opens the PR.
Workflow
1. The verdict — one pass, four questions
Read the diff yourself — never delegate this pass; mid-build scrutiny was dw-check's job. Every
finding sits at a real file:line you opened, and when you already trust the diff, say so and go
straight to closing.
- Correct? — the goal's behaviour, plus the edge case, the error path, the empty input.
- Does it fit? — a pattern used once elsewhere in this repo beats a better one used nowhere.
- Blast radius? — what else reaches this code; name every one-way door (migration, data deletion, renamed public API) as irreversible.
- Is "done" proven? — name the rung each claim reached: said so · pointed at the line · showed
the bad case impossible · ran it · reproduced it in the artifact a user gets. A claim short of
"ran it" is spoken aloud, never written up as settled. Read the rung off the boxes rather than
deriving it again: a ticked task names in its
proof:what was run against it, and a box ticked with nothing run, or carrying no check to run, issaid sohowever finished the code looks.
The completion gate: read the ## Goal against the diff, not the checklist — an
undelivered result is not ready, never "ready with follow-ups"; finish it, or the user amends
the goal. One carve-out: a result only CI can show is pending on the push, handed to dw-ship.
Close with one line — ready to merge, ready with follow-ups, or not ready and why — and sort each follow-up: done now (phase 2 starts by doing it) · report-open (a line in the report and PR body) · backlog (genuinely exceeds the session). Then stop: the user decides what happens next.
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.
- yesterday Changed · +5 lines · +3 tokens per session 5e02f89d5fc8
- 3d ago Changed · +21 lines f138a22eea0d
- 5d ago Changed · +2 lines · +3 tokens per session 36292238fe46
- 7d ago Changed · +4 lines 55853563bc6a
- 8d ago Changed 4ad84892d84e
- 12d ago First seen · 104 lines · 68 tokens per session scan A 3aa015c89cf3
dw-land is a skill published in the GitHub repository dominikwozniak/dw-solo-skills (2 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 2,202 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
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.
cleanup
Clean up after a merged pull request — return to the base branch, remove the worktree, delete the branch, sweep other stale branches and worktrees, and report tracker state. Use after a merge or whenever asked what is left over.
merge
Merge the reviewed pull request for the current branch, then hand straight off to cleanup. A sentence of editorial direction alongside the green light is read as a rider. Use when a human green-lights an open PR.
github-design
Use when setting up GitHub repositories, workflows, issue templates, or project organization - enforces best practices for .github folder structure, reusable workflows, branch protection, CODEOWNERS, labels, and GitHub Projects. Triggers on: GitHub, repository setup, workflow, Actions, issue template, PR template…
gate-check
Audit current work against all seven GENESIS gates before a commit or at the end of a task. Runs the project check command, finds unregistered files, orphan TODOs, doc-sync drift, and missing registry entries. Use when the user asks to gate-check, audit gates, verify gates, or before committing in a GENESIS project…