A controlled task runner for the execution part of the STAR workflow. It follows a dispatch brief and may write only artifacts that the brief and task explicitly allow.

Use it for an approved implementation phase, a bounded collector, or a read-only review under a STAR dispatch brief.

It keeps implementation work within defined file, permission, and write boundaries instead of letting a delegated task make unrelated changes.

How wanghao9610/STAR configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/wanghao9610/STAR/main/.claude/agents/star-exec.md

Clone the repo

git clone --depth 1 https://github.com/wanghao9610/STAR

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/wanghao9610/star/star-exec/github.svg)](https://agentmods.dev/agents/wanghao9610/star/star-exec)

Your own site

<a href="https://agentmods.dev/agents/wanghao9610/star/star-exec"><img src="https://agentmods.dev/badge/agents/wanghao9610/star/star-exec/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/wanghao9610/star/star-exec"><img src="https://agentmods.dev/badge/agents/wanghao9610/star/star-exec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 176 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00021	$0.00176
Opus 5.5	$0.00008	$0.00070
Sonnet 5.5	$0.00004	$0.00035
Haiku 4.5	$0.00002	$0.00018

Measured 2mo ago against content hash 000f8fd467a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

star-exec 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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

star-plan — 86% identical, 8 lines differ

.claude/agents/star-exec.md · 17 lines

What it actually says

Carry out only the STAR execution-tier work named in the dispatch brief. Preserve the invocation and tier tokens, and use the brief as the boundary of your authority.

For a complete skill or phase, read the named skill manifest in full before acting. For a bounded collector brief, read only its exact file list and return only its requested form; do not load the manifest for context. For a blind review, read only the artifact and rubric the brief names.

Write only when the brief and the skill authorize a named artifact. A collector or blind review is read-only: do not edit files, change state, or run a state-changing shell command. Return the requested evidence or result directly to the caller.

Changes

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.

2mo ago First seen · 17 lines · 21 tokens per session scan A 000f8fd467a6

Subscribe to this mod's changes

star-exec is an agent published in the GitHub repository wanghao9610/STAR (54 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 176 once invoked, about $0.0001 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 2026-09-07.

Building agents Project Management harness workflow

star-exec next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
star-execwanghao9610/STAR	Agent	54	2d ago	MIT	A	21	Claude Code
flow-gap-analystgmickel/flow-next	Agent	717	yesterday	MIT	A	21	Claude Code
checkmindfold-ai/Trellis	Agent	15k	1mo ago	AGPL-3.0	A	34	Claude Code
code-quality-reviewerbabyworm/rtl-agent-team	Agent	67	1mo ago	MIT	A	62	Claude Code
data-etl-workerdwarvesf/dwarves-kit	Agent	13	yesterday	MIT	A	70	Claude Code
rtl-plannerbabyworm/rtl-agent-team	Agent	67	1mo ago	MIT	A	43	Claude Code
workflow-orchestratorNickCrew/Claude-Cortex	Agent	66	4mo ago	MIT	A	74	Claude Code

STAR: Agent for Claude Code