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 TweekFawkes/prompts --skill doworkgit clone --depth 1 https://github.com/TweekFawkes/promptsWrote 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/tweekfawkes/prompts/dowork)<a href="https://agentmods.dev/skills/tweekfawkes/prompts/dowork"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/dowork/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/tweekfawkes/prompts/dowork"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/dowork.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 | $0.00045 | $0.02086 |
| Opus 5.5 | $0.00018 | $0.00834 |
| Sonnet 5.5 | $0.00009 | $0.00417 |
| Haiku 4.5 | $0.00005 | $0.00209 |
Grade A, and why
dowork 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 1mo 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drain the ticket queue
Drains the open ticket backlog. The user is away; never ask questions, never stop the loop for one blocked ticket.
Preconditions
- Confirm
git branch --show-currentis on any branch other thanmain, inside an Orca worktree, not the canonical checkout. If either is false, stop and say so. - Install dependencies as CLAUDE.md says, if not already done.
- Read the newest file in
z/handoffs/(highest timestamp) other thanREADME.md, for what is already true on disk; if none exists, run/handofffirst so progress has somewhere to land. python3 .claude/skills/do_all/scripts/queue.py listto get the queue in pick order.
Loop, one ticket at a time
Pick order is priority tier first, then NNN: tier order is user, must, nice from each
ticket's Priority: line (a missing line counts as user), and within a tier the lowest NNN
runs first. Only tickets whose Depends on tickets are all in closed/ qualify; skip tickets
whose Status is blocked. queue.py next prints exactly that pick, so never compute it by hand.
If an argument names a specific ticket file, do that one first. --one stops the loop after one
ticket closes or blocks, and combines with a filename: /dowork <file> --one does that ticket
and nothing else. --until NNN stops once a ticket numbered NNN has closed or blocked. A ticket
with Owner: primary is executed by the primary session itself (no worker dispatch): follow the
ticket's Steps, then close it as below, under the attempt ladder's three-round cap — after three
failed rounds, mark it blocked and continue or stop per the normal rules. A ticket whose Steps run
/ship is last: /ship closes it and writes the final handoff itself; steps e, f, and g are
skipped, and the loop ends after /ship returns.
a. Dispatch the worker. Call the Agent tool with subagent_type: worker and this exact prompt,
filling in the two paths. The primary session does not read the ticket body beyond its title
and ## Acceptance lines; the worker reads the rest.
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.
- 1mo ago Changed · -25 lines · -126 tokens per session e9e932f17c9b
- 2mo ago First seen · 152 lines · 171 tokens per session scan A ed22d275c0eb
dowork is a skill published in the GitHub repository TweekFawkes/prompts (2 stars, last pushed 1mo ago), licensed Unlicense. It adds 45 tokens to every session and 2,086 once invoked, about $0.0002 per session on Opus 5.5. 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
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.