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.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 5.1 | $0.00000 | $0.02637 |
| Opus 5 | $0.00000 | $0.01319 |
| Sonnet 5 | $0.00000 | $0.00527 |
| Haiku 4.5 | $0.00000 | $0.00264 |
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 today.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drive the workflow toward a goal
The user has typed star-auto — this file is what that invocation runs. Typing it is the auto grant of conventions §10.7: while this run pursues its goal, the skill each next action names may be started without further naming, the seven explicit-only ones included, and a prepared STOP-line command may be launched instead of handed back. At involve=low, that same explicit grant also covers the executor chain's routine local implementation, mechanical review fixes, and Git lifecycle described below; a started run otherwise behaves exactly as if the user had typed its name.
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: an autonomous run takes the marked recommendation on its own judgment calls and logs each (§7.8). Atlow, the invocation itself pre-approves the executor's recommended 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. Those operations run without an authorization question and are logged. Review fixes that require deletion are skipped and routed rather than guessed. The merged execution branch is retained without asking, so unattended cleanup never needs a forced delete. This exception is carried to the executor and code reviewer as the internalauto=unattendedtoken; it 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, the run is uncapped: prepared STOP-line commands launch autonomously, the goal owning the run (§2's one exception). Either way every launch is logged in the decisions record with its stated cost. Apart from the clean worktree removal above, neither the grant 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 — those stop and report instead of being guessed through. - 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.
- today Changed · +1 lines 071122d5933a
- 8d ago First seen · 54 lines · 0 tokens per session scan A 8cd96237929d
star-auto is a command published in the GitHub repository wanghao9610/STAR (51 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,637 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.
Other commands, from other repositories
triage
Triage Linear issue with comprehensive analysis.
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
sync
Manually trigger plan-sync to update downstream task specs after implementation drift.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
audit-search
Búsqueda contextual en audit trail — fecha, acción, usuario, proyecto, confianza. NL search y regex.
banking-detect
Auto-detectar proyecto bancario por entidades BIAN, Kafka, Snowflake, SWIFT.