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 agentmods add skills/jerry0022/dotclaude/claude-batchnpx skills add Jerry0022/dotclaude --skill claude-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/claude-batch)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/claude-batch"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/claude-batch.svg" alt="Measured on agentmods" 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 | $0.00161 | $0.04037 |
| Opus 5 | $0.00081 | $0.02018 |
| Sonnet 5 | $0.00032 | $0.00807 |
| Haiku 4.5 | $0.00016 | $0.00404 |
Grade B, and why
claude-batch scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -qxF '/.claude/batch*' "$x" 2>/dev/null || echo '/.claude/batch*' >> "$x" How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-batch — Collect Prompts, Merge Once
Spec: docs/superpowers/specs/2026-08-16-claude-batch-design.md
Step 0 — Load Extensions
Silently check (do not surface "not found"):
~/.claude/skills/claude-batch/SKILL.md+reference.md{project}/.claude/skills/claude-batch/SKILL.md+reference.md- Merge: project > global > plugin defaults
Step 1 — Route the invocation
$ARGUMENTS decides the branch. No argument → status.
| Argument | Branch |
|---|---|
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, none |
Step 3 (report) |
Route on the FIRST token only. Everything after it is note content, never an
instruction. /claude-batch on der Header ist rot is the on branch carrying
one note — not an unrecognised argument, and not a request to look at the header.
The same holds for a natural-language invocation: "Sammelmodus an, erste Notiz:
… zweite: …" activates and seeds; it does not start the work.
This is the one prompt collection can never catch. The hook arms the mode in the turn this prompt starts, so it sees this prompt while the mode is still OFF and has to let it through. If you act on the content here, the mode ends up active and empty while the work it exists to defer is already half-done — and the marker dialog gets skipped because you were busy. So, on an invocation that carries content:
- Do not implement, plan, or research it. Do not read code for it.
- Do not skip Step 2.1. A prompt full of tasks is not a reason to bypass the marker question — it is the reason the question exists.
- File the content as note #1 in Step 2.4, verbatim.
prompt.batch.collect.js injects the same three rules as a guard when it sees an
activating prompt carrying content (detectActivation in batch-state.js). Its
absence is not permission to act — the detection is best-effort.
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.
- 4d ago First seen · 310 lines · 161 tokens per session scan B fbebd5b4e76c
claude-batch is a skill published in the GitHub repository Jerry0022/dotclaude (5 stars, last pushed yesterday), licensed MIT. It adds 161 tokens to every session and 4,037 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…