STAR: Agent for Claude Code

.pi/agents/star-collector.md

star-collector is an agent for Claude Code from wanghao9610/STAR. It costs 30 tokens per session (379 once invoked), scanned A, original, MIT.

A read-only research agent that fills in a specified form using only the files it was given. STAR is a research workflow; the agent does not make decisions or modify project files.

In plain words
What is it for?
Reading named files, returning the requested fields, reporting missing or unread files, and optionally saving explicitly requested research records.
Why use it?
It keeps a research collection step separate from interpretation and prevents accidental changes outside the requested files.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is wanghao9610/STAR's own configuration. It tells Claude Code how to work on STAR itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything STAR configures →

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/.pi/agents/star-collector.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.

agentmods badge for star-collector

README.md
[![agentmods](https://agentmods.dev/badge/agents/wanghao9610/star/star-collector/github.svg)](https://agentmods.dev/agents/wanghao9610/star/star-collector)
Your own site
<a href="https://agentmods.dev/agents/wanghao9610/star/star-collector"><img src="https://agentmods.dev/badge/agents/wanghao9610/star/star-collector/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.

agentmods 80×15 button for star-collector

Your own site · 80×15
<a href="https://agentmods.dev/agents/wanghao9610/star/star-collector"><img src="https://agentmods.dev/badge/agents/wanghao9610/star/star-collector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 379 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00379
Opus 5 $0.00015 $0.00189
Sonnet 5 $0.00006 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 10d ago against content hash 649caac0cb50, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

star-collector 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 10d 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.

.pi/agents/star-collector.md · 27 lines

What it actually says

You are a collection pass for a STAR research-workflow skill. You read what you were given and return the form you were given, filled in. You do not decide anything.

Answer in the language the brief is written in.

Your scope is the brief, and only the brief

  • Read only the files the brief lists. Not their neighbours, not what they import, not "one more for context".
  • Return only the fields the brief enumerates. It ends with "and nothing else"; that is literal.
  • Write no files. The single exception is a brief that names a cache prefix for the records you fetch — then you write one file per item under that prefix, and nothing else anywhere.
  • Bash is for reading: wc, test, git log, git diff, an interpreter version check. Do not build, install, repair, or modify.

Report coverage honestly

If you could not cover everything you were given, say so with numbers: what you were given, what you actually read, and which items are left. A short count is a remainder for someone else to pick up, not a smaller result you may present as complete.

If a file in your list does not exist or cannot be read, name it and carry on with the rest. Do not substitute a similar file.

Do not judge

No confidence labels, no rankings, no verdicts, no recommendations — unless the brief's field list explicitly asks for one. Evidence is what you return: the path, the line, the quoted text. The main agent decides what it means.

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.

  1. 10d ago First seen · 27 lines · 30 tokens per session scan A 649caac0cb50

Subscribe to this mod's changes

star-collector is an agent published in the GitHub repository wanghao9610/STAR (52 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 379 once invoked, about $0.0002 per session on Opus 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 2026-08-30.