Borrowing it
Nothing to install: this file belongs to wanghao9610/STAR. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wanghao9610/STAR/main/.agents/commands/star-auto.mdgit clone --depth 1 https://github.com/wanghao9610/STARWrote 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/commands/wanghao9610/star/star-auto)<a href="https://agentmods.dev/commands/wanghao9610/star/star-auto"><img src="https://agentmods.dev/badge/commands/wanghao9610/star/star-auto/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/commands/wanghao9610/star/star-auto"><img src="https://agentmods.dev/badge/commands/wanghao9610/star/star-auto.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 | $0.00000 | $0.03432 |
| Opus 5.5 | $0.00000 | $0.01373 |
| Sonnet 5.5 | $0.00000 | $0.00686 |
| Haiku 4.5 | $0.00000 | $0.00343 |
Grade A, and why
star-auto 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 14d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drive the workflow toward a goal
Use this procedure when the user requests star-auto with a stated goal. Within that request, conventions §10.7 covers starting the skills needed for the goal, including the seven explicit-only skills, and prepared STOP-line launches that meet the conditions below. At involve=low, the requested workflow also includes the executor chain's routine local implementation, mechanical review fixes, and Git lifecycle described below. Each started run keeps its skill's scope and artifact ownership, the user's limits, and the host's permission requirements.
Invocation shape: star-auto <goal> [stop=<stop line>] [involve=<level>].
Parse the invocation
- Strip
involve=<level>first, taken from outside the stop text — beforestop=, or as the invocation's final token; the same words inside the stop line are stop-line text, not the token (conventions §7.7). When nothing sets a level — no token, noINVOLVEin.env— this run resolves tolow, notmedium: it takes the marked recommendation on routine judgment calls and logs each (§7.8). Atlow, the requested workflow includes the executor's recommended in-scope plan, explicit-path staging and commits, execution-branch or worktree creation, behavior-preserving review fixes that delete nothing, a clean reviewed squash merge, and removal of a worktree only after its durable artifacts have moved out andgit status --porcelainis empty. Reuse that workflow decision and log each operation; obtain any approval the host separately requires. Review fixes that require deletion are skipped and routed. Retain the merged execution branch. Pass the internalauto=unattendedtoken to the executor and code reviewer with the originating user request, goal and limits in the dispatch brief or run record (conventions §10.7); the token only carries that existing scope and is not part of the user-facing invocation shape. - Then strip
stop=: everything from that token to the end of what remains is the stop line, natural language in the user's own words —stop=any single training over 4 hours, or any paid API call,stop=用卡超过 2 张就停(either language, or both at once). Given, it is the line this run must not cross: before launching a prepared command, state its expected cost and judge it against each condition — a command that crosses the line, or that cannot be judged against it, is printed and handed back exactly as §2 says. Absent, no additional workflow cost ceiling was set: prepared commands may launch within the goal after their resource scope and cost are assessed, their review is current, and host permission allows them (§2). Either way every launch is logged in the decisions record with its stated cost. Apart from the clean worktree removal above, neither the request nor any stop line covers deletion, overwrite,sudo, system or driver installation, history rewriting, forced Git,push, discarding unmerged work, or resolving a merge conflict — retain the state and report the missing specific authority. - What remains is the goal. No goal — ask for one; never infer a goal from the repository.
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.
- 14d ago Changed · +17 lines 3adf2e46df10
- 1mo ago Changed e2b4462e87f1
- 1mo ago Changed 3d8763ab5f5c
- 2mo ago Changed · +1 lines 071122d5933a
- 2mo ago First seen · 54 lines · 0 tokens per session scan A 8cd96237929d
star-auto is a command published in the GitHub repository wanghao9610/STAR (54 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,432 tokens. 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 2026-08-30.
star-auto compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| star-autowanghao9610/STAR | Command | 54 | 2d ago | MIT | A | 0 | Claude Code |
| triagen8n-io/n8n | Command | 210k | yesterday | none | A | 7 | Claude Code |
| landgmickel/flow-next | Command | 717 | yesterday | MIT | A | 13 | Claude Code |
| syncgmickel/flow-next | Command | 717 | yesterday | MIT | A | 15 | Claude Code |
| webapp-testinghamr0/agentic-toolkit | Command | 23 | 6d ago | Apache-2.0 | A | 35 | Claude Code |
| link-projecttechnicalpickles/pickled-claude-plugins | Command | 12 | yesterday | MIT | A | 9 | Claude Code |
| uninstallgmickel/flow-next | Command | 717 | yesterday | MIT | C | 9 | Claude Code |