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 auto-agentsgit 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/auto-agents)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/auto-agents"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-agents/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/auto-agents"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-agents.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 | $0.00184 | $0.07438 |
| Opus 5.5 | $0.00074 | $0.02975 |
| Sonnet 5.5 | $0.00037 | $0.01488 |
| Haiku 4.5 | $0.00018 | $0.00744 |
Grade B, and why
auto-agents 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
were used but are NOT covered by the current `~/.claude/settings.json` How it starts
The opening of the file, as written. The whole thing — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auto-agents — the execution path
Every skill that implements executes through this one: do-run,
auto-concept (implement click and close-out follow-ups), auto-fix,
auto-harden, auto-polish. It decides how the work runs — inline, one
agent, parallel agents or the full wave ceremony — by the always-on
delegation policy (deep-knowledge/agent-proactivity.md), shows what it is
about to run, runs it, and returns the result to its caller.
This skill invokes no skill. It sits at the bottom of the call graph
(layer 5, invokes: []) because it only spawns role agents. Everything that
would need another skill — shipping, a concept page, an issue — is returned
to the caller as a field of the result (Step 7), and the caller decides.
Spawned agents follow the same rule: they report, they do not start skills.
Step 0 — Load Extensions
Injected by the override loader ([skill-overrides] block); none shown → none exist.
Step 1 — Inputs: arguments, plan and usage
Arguments
| Argument | Set by | Meaning |
|---|---|---|
--from=<caller> |
every calling skill: do-run, auto-concept, auto-fix, auto-harden, auto-polish |
Who gets the result (Step 7). Absent = the model invoked this skill directly — the user said yes to the full-ceremony offer or typed a trigger phrase; the main conversation is then the caller. |
--mode=interactive|background |
the caller | The execution mode — the former Step 4 question. do-run answers it with its question 2 ("Ablauf?"): Interaktiv · … → interactive, Autonom · … → background. auto-concept passes background (its main session keeps the heartbeat and /status posts). auto-fix, auto-harden, auto-polish pass background under --autonomous, else interactive. |
--ship=auto|manual |
do-run (question 2) |
Echoed in the result, never acted on. Missing = manual. |
--burn=<path> |
do-run's burn and backlog modes (via autonomous mode) | The run's BURN-STATE.json. Replaces tiers and waves with the burn conveyor (Step 6): burn-plan.js gate decides every spawn, each task lands on its own. |
| rest | the caller | The task or the approved plan, verbatim — decisions, file paths, the concept file, the root cause. Never a paraphrase. |
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 971d0fd2ccf8
- 15d ago Changed · +10 lines f57f1775841e
- 16d ago Changed · +2 lines cb36b9f9be2b
- 18d ago Changed · +2 lines 21989601d005
- 21d ago Changed · -2 lines 9433e6daf569
- 1mo ago Changed · +8 lines fd4e63497610
- 1mo ago Changed faee4ba80cfb
- 1mo ago Changed · +1 lines 7cafe6de9990
- 1mo ago Changed 58d94cc99c98
- 1mo ago First seen · 481 lines · 184 tokens per session scan B 36d873236b50
auto-agents is a skill published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 184 tokens to every session and 7,438 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-24.
auto-agents compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| auto-agentsJerry0022/dotclaude | Skill | 6 | 11d ago | MIT | B | 184 | 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 |