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 do_allgit 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/do_all)<a href="https://agentmods.dev/skills/tweekfawkes/prompts/do_all"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/do_all/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/do_all"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/do_all.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 | $0.05350 |
| Opus 5.5 | $0.00031 | $0.02140 |
| Sonnet 5.5 | $0.00016 | $0.01070 |
| Haiku 4.5 | $0.00008 | $0.00535 |
Grade A, and why
do_all 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Do all
Runs from the canonical checkout on main. This session is a thin dispatcher: it picks the next
ticket, cuts a worktree, launches a child Claude session there, waits, checks ground truth on
disk and on GitHub, syncs main, logs one line, and repeats. It never edits code, never reads a
diff, and never commits on main. The user is away: never ask, never stop for one failed ticket.
Set PREFIX in every prelude below to the same branch prefix as CLAUDE.md (default agent).
Child branches are $PREFIX/da-NNN-slug. Add z_loops/ to the repo's .gitignore — run state
is host-local and must not be committed.
Why the tiers exist
Earlier unattended loops stalled because child sessions filed follow-up tickets and then worked
those before the tickets the human wrote. Every ticket now carries Priority: user | must | nice
(z/tickets/README.md). This loop works every user ticket first, then must, then nice;
scripts/queue.py recomputes that order from disk each iteration, so nothing a child files can
jump the queue. A child can only file must or nice (/dowork step f), and a ticket that a
child branch ($PREFIX/da-*) introduced while claiming user is demoted to must before it
can be picked (step 2c). A user ticket that reaches main any other way mid-run stays user.
Flags
--dry-run: print the queue order and the first pick; create nothing, touch no run state.--max N: stop after N tickets were attempted (default 30).--tiers user,must,nice: which tiers to work, always in this order (default all three;--tiers userworks only the human's tickets).--resume: reuse the newest run underz_loops/do_all/(its manifest and attempted list) instead of starting a new one.--clean: after a verified merge, remove the worktree and its local branch withorca worktree rm(default keeps them and closes only the child terminal).
Shell rules for every block below
The Bash tool runs zsh and forgets variables between calls. Every block therefore starts with
this prelude (written <prelude> below):
What ships with it
2 files 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.
- 1mo ago First seen · 313 lines · 0 tokens per session scan A bce2524b7f1d
do_all is a skill published in the GitHub repository TweekFawkes/prompts (2 stars, last pushed 1mo ago), licensed Unlicense. It adds 78 tokens to every session and 5,350 once invoked, about $0.0003 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 2026-09-20.
Other skills, from other repositories
antfu-issue-triage
Triage open issues and PRs of the current GitHub repo - find already-fixed, duplicate, and spam items, suggest labels, gauge demand from reactions and comments, then present a table of proposed actions and comments for confirmation before touching anything. Use when asked to triage, organize, clean up, or groom issues…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the zai-glm-flash smoke test), open code review (ocr)…
connect
Choose which wiki this session uses, the team project's pages on the Nimbalyst server or the project's local wiki of files, and connect a repository to its team project. Use at the start of a task before any wiki tool, when a wiki tool returns reponotbound, ambiguousproject, pinmismatch, projectnotaccessible…