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 Jerry0022/dotclaude --skill do-batchgit clone --depth 1 https://github.com/Jerry0022/dotclaudeWrote 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/jerry0022/dotclaude/do-batch)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/do-batch"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/do-batch/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/jerry0022/dotclaude/do-batch"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/do-batch.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 | $0.00135 | $0.06675 |
| Opus 5.5 | $0.00054 | $0.02670 |
| Sonnet 5.5 | $0.00027 | $0.01335 |
| Haiku 4.5 | $0.00014 | $0.00668 |
Grade A, and why
do-batch 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 11d 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
do-batch — Collect Prompts, Merge Once
Spec: docs/superpowers/specs/2026-08-16-claude-batch-design.md
Step 0 — Load Extensions
Injected by the override loader ([skill-overrides] block); none shown → none exist.
Step 1 — Route the invocation
$ARGUMENTS decides the branch. No argument → activate when the mode is
off, status when it is already on.
| Argument | Branch |
|---|---|
| none | Mode off → Step 2 (activate). Mode on → Step 3 (report). The bare invocation IS the request to collect — nobody types /do-batch to be told the mode is off |
on, an, start |
Step 2 (activate) |
off, aus, stop |
Step 5 (deactivate) |
go, los, merge |
Step 4 (fire) |
marker |
Step 2.1 (ask again, overwrite the stored marker) |
status |
Step 3 (report) |
help, hilfe, ? |
Step 6 (print the long-form help, nothing else) |
| anything else (free text) | Content fallback — the whole argument is a note: activate the mode if it is off (Step 2, including the marker question), file the text verbatim as note #1 (Step 2.4), report the count |
Activation ends ON. After Step 2 — marker question included — the mode is
running and the user's next prompt is collected. Never end the activating turn
with "type /do-batch on to start": that is the turn they just spent, and
it is why they invoked the skill in the first place.
While the mode is on, the hook absorbs a re-activation. /do-batch,
/do-batch on, /do-batch <text> and /do-batch help are blocked
by prompt.batch.collect.js (classify → rearm): free text becomes a note,
help prints renderHelp, and otherwise the user sees the short rearm panel
(status line + renderCommandLines) instead of paying a turn.
You only see such an invocation when it carried an attachment — then it is the
content fallback, filed per Step 2.6. off, go, status and marker always
reach you.
Marker pre-check — on EVERY route, before the route's own work. Call
loadConfig(). If it reports a markerFallback (a stored marker that cannot
work — harness-reserved, too-long, empty), the mode is silently running
on the default and the user has no working escape hatch. Do not merely report
that: ask the Step 2.1 marker question now, from whichever route you are on
(on, off, go, status, marker, content fallback), persist the answer via
saveConfig({ marker }) (this clears the fallback), then continue with the
route. Only the marker route stops after the question.
What ships with it
3 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.
- 11d ago Changed 648424326ebb
- 15d ago Changed · +7 lines c34a112746c0
- 16d ago Changed · -4 lines 19a2e2ca6f1b
- 18d ago Changed · +5 lines 269a585c6f13
- 28d ago Changed · +6 lines dac3c7404ce4
- 1mo ago Changed · -27 lines f205272257f1
- 1mo ago Changed · -106 lines scan B → A 0d45ddc5c565
- 1mo ago Changed · +1 lines 0189f0c8a898
- 1mo ago Changed · +6 lines c98e87d73e7e
- 1mo ago First seen · 589 lines · 135 tokens per session scan B b7d34fe9c024
do-batch is a skill published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 135 tokens to every session and 6,675 once invoked, about $0.0005 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 2026-09-24.
do-batch compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| do-batchJerry0022/dotclaude | Skill | 6 | 11d ago | MIT | A | 135 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |