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.
npx skills add dominikwozniak/dw-solo-skills --skill dw-prunegit clone --depth 1 https://github.com/dominikwozniak/dw-solo-skillsWrote 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-prune)<a href="https://agentmods.dev/skills/dominikwozniak/dw-solo-skills/dw-prune"><img src="https://agentmods.dev/badge/skills/dominikwozniak/dw-solo-skills/dw-prune/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-prune"><img src="https://agentmods.dev/badge/skills/dominikwozniak/dw-solo-skills/dw-prune.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 | $0.00050 | $0.00759 |
| Opus 5 | $0.00025 | $0.00380 |
| Sonnet 5 | $0.00010 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
dw-prune 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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dw-prune — the queue stops being a record of everything you once considered
A backlog grows by append, and nothing else in the loop reads it end to end — so a stale entry outlives what it described and the folder becomes a list you skim. This walks it once, deliberately.
What it reads and writes
Every .ai/backlog/*.md except README.md, the folder's own contract rather than a queued idea —
the whole folder every time, so it takes no arguments. It
writes deletions, a rewrite of any entry it bundles into, and the fix itself where one is cheap enough
to close here. .ai/ is tracked in git. It shapes nothing: an entry that is real work stays for
dw-shape.
Workflow
1. Read the folder's own bars first
.ai/backlog/README.md states them — will you ever? and should it have been done now? — with
the entry shape and, where the repo caps the list, what a full one costs. Judge against those, not
against taste.
2. One pass, four outcomes, every entry gets one out loud
Oldest first — the date prefix sorts them, so the folder reads in that order already:
- Stale or already done — the code moved on, another change closed it, the tool is gone.
git rmit, reason in the commit message. A queue you never delete from is a record. - Cheap and unblocked — the absorption bar, applied late. Do the work now and
git rmthe entry in the same commit, the fix and the deletion together. Where an open change is checked out in this tree, that commit belongs to it; otherwise it is a commit here. Never reach into a change living in another worktree — you cannot commit there, and this pass only ever commits in the tree it runs in. - Bundled — an entry that would ship with a cousin (same version bump, same gate run, one PR)
merges into it. Rewrite the survivor to cover both,
git rmthe other. - Stays — real work whose moment hasn't come. Say so, write nothing. On a healthy folder most entries end here, and that is the right answer.
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.
- 5d ago Changed · +1 lines 6fa5296578f4
- 8d ago Changed c51ab964158e
- 12d ago First seen · 61 lines · 50 tokens per session scan A 277699aee495
dw-prune is a skill published in the GitHub repository dominikwozniak/dw-solo-skills (2 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 759 once invoked, about $0.0003 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.