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-rungit 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-run)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/do-run"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/do-run/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-run"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/do-run.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 | $0.00202 | $0.05032 |
| Opus 5.5 | $0.00081 | $0.02013 |
| Sonnet 5.5 | $0.00040 | $0.01006 |
| Haiku 4.5 | $0.00020 | $0.00503 |
Grade A, and why
do-run 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Do Run
One door for every multi-step run. This file is the router: it asks one question call, at most one follow-up, then runs the matching mode file. Each mode file is the verbatim body of a former skill; where the router already answered one of its questions, the mode file says so and reads the answer.
Step 0 — Load Extensions
Injected by the override loader ([skill-overrides] block); none shown → none exist.
Step 1 — Machine prompts and presets
Machine prompts never see a question. Route them straight into the mode and skip Steps 2–5:
| Prompt starts with | Follow |
|---|---|
AUTONOMOUS_AUTOSTART: |
modes/autonomous.md Step 0.1 |
AUTONOMOUS_RESUME: |
modes/autonomous.md Step 0.2 |
RUN_BACKLOG_AUTOSTART: |
modes/backlog.md Step 0.1 |
BURN_RESUME: |
modes/burn.md Step 0.6 (the prompt.burn.resume hook names the policy) |
The same holds while an AFK lockout is active
(node "{PLUGIN_ROOT}/scripts/autonomous-lockout.js" check →
active: true): take the click-through answers (every first option, Step 3)
without asking.
Presets. An unambiguous signal in $ARGUMENTS or the prompt answers a
question in advance. A preset drops the question (or the option) from the
call and is stated in one line before it ("Was: Backlog — aus dem Prompt").
It never reorders the options that remain.
| Signal | Effect |
|---|---|
--from=do-batch |
Q1 dropped — the merged batch plan is the prompt (Prompt umsetzen). |
backlog, or a backlog trigger phrase |
Q1 dropped → Backlog. |
audit, or an audit trigger phrase |
Q1 dropped → Audit. |
autonomous, or an AFK phrase ("while I'm away", "afk", "autopilot") |
Q2 shows only its two Autonom · … options, in table order. |
rethink, or a stuck phrase (the rethink triggers above) |
Q4 marks "Rethink vorher" as recommended. |
sleep, or a first-person bedtime phrase ("gute Nacht", "ich gehe ins Bett", "geh schlafen", "going to bed") |
Q2 only Autonom · …, Q3 dropped (Flexibel), F6 always asked and moved into the base call, the base call gets the 3-minute autostart; nothing left to do → F6 alone. Details: deep-knowledge/questions.md (Bedtime). |
| a ship wish in the task ("inkl. ship", "und shippen", "ship it when green", "ship when done") | Q2 shows only its … · Ship automatisch options. |
| a shutdown, resume or desktop-takeover wish | F6 / F5 dropped → the named option; phrases: deep-knowledge/questions.md § Follow-up questions. |
literal burn (/do-run burn, /run-burn) |
Budget verbrennen is on; the option leaves Q4 whatever the usage. |
strict already armed for this branch (node "{PLUGIN_ROOT}/hooks/lib/strict-state.js" status → active: true, reason: "on") |
Q3 dropped → Strikt (strict off lifts it, not this question). |
What ships with it
24 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.
- autonomous-start-gate.test.js 4.9 KB runs code
- burn-wiring.test.js 5.6 KB runs code
- deep-knowledge-pointers.test.js 2.1 KB runs code
- deep-knowledge/execution.md 7.0 KB
- deep-knowledge/questions.md 12 KB
- do-run-questions.test.js 18 KB runs code
- do-run-rethink.test.js 7.3 KB runs code
- modes/audit.md 15 KB
- modes/audit/deep-knowledge/dimensions.md 7.4 KB
- modes/autonomous.md 41 KB
- modes/autonomous/deep-knowledge/html-report.md 2.3 KB
- modes/autonomous/deep-knowledge/shutdown-watchdog.md 18 KB
- modes/autonomous/evals/evals.json 2.8 KB
- modes/backlog.md 34 KB
- modes/backlog/finalizer-deferral.test.js 4.3 KB runs code
- modes/backlog/presence-shutdown.test.js 2.6 KB runs code
- modes/backlog/reference.md 2.1 KB
- modes/burn.md 13 KB
- modes/burn/deep-knowledge/burn-scheduler.md 15 KB
- modes/burn/deep-knowledge/composite-prompt.md 2.8 KB
- modes/rethink.md 12 KB
- modes/rethink/deep-knowledge/lenses.md 4.1 KB
- run-contract-text.test.js 6.7 KB runs code
- triggers.de.txt 116 B
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 · +11 lines a6d1090806e4
- 15d ago Changed 6932337c862f
- 16d ago Changed · -3 lines a874ad6e3d0a
- 21d ago Changed · +1 lines 3d5853a620b6
- 23d ago Changed · +19 lines · +4 tokens per session c049516954f2
- 1mo ago Changed · +1 lines · -171 tokens per session a4b8db445ef5
- 1mo ago Changed · +1 lines d345b9c428bc
- 1mo ago Changed 7704b03bc364
- 1mo ago Changed · +1 lines · +9 tokens per session 66a374ff6466
- 1mo ago First seen · 251 lines · 360 tokens per session scan A 1f984966f02d
do-run is a skill published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 202 tokens to every session and 5,032 once invoked, about $0.0008 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-run compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| do-runJerry0022/dotclaude | Skill | 6 | 11d ago | MIT | A | 202 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |