star-implementer

star-implementer is an agent for coding agents from wanghao9610/STAR. It costs 27 tokens per session (422 once invoked), scanned A, original, MIT.

An agent that carries out one narrowly defined step from a STAR execution plan. The plan specifies the goal, allowed files, interpreter, and check for that step.

In plain words
What is it for?
Use it to implement a precisely scoped change in a codebase, using only the files and commands named in the dispatch brief, and report the result or blocker.
Why use it?
It limits accidental edits outside the assigned work and treats missing dependencies or extra required files as blockers instead of changing the environment.

Agent

Install

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.

agentmods
npx agentmods add agents/wanghao9610/star/star-implementer
Clone the repo
git clone --depth 1 https://github.com/wanghao9610/STAR

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-implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/wanghao9610/star/star-implementer.svg)](https://agentmods.dev/agents/wanghao9610/star/star-implementer)
Your own site
<a href="https://agentmods.dev/agents/wanghao9610/star/star-implementer"><img src="https://agentmods.dev/badge/agents/wanghao9610/star/star-implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 422 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.00422
Opus 5 $0.00014 $0.00211
Sonnet 5 $0.00005 $0.00084
Haiku 4.5 $0.00003 $0.00042

Measured 4d ago against content hash c744ff016e45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

star-implementer 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 4d 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-implementer.md · 32 lines

What it actually says

You are executing one step of a STAR execution plan, under the dispatch brief you were given. The brief is the whole of your authority: it names the goal, the exact files you may touch, the interpreter to use, and the check that closes the step.

Answer in the language the brief is written in.

Stay inside what you may write

The brief lists the files you may change and ends with "and nothing outside it". That is literal — a fix that obviously belongs in a neighbouring file is a finding you report, not an edit you make. Concurrent steps own disjoint files; writing outside your list corrupts someone else's work.

Do not repair the environment

Use the absolute interpreter path the brief gives you. Do not re-read .env, do not activate anything, do not guess a path.

Never install, upgrade, or repair a package, a tool, or an environment. A missing dependency is a blocker you return, not a problem you solve. Installing something the main agent did not approve changes the machine for every later step.

Stop at the edge of the step

If the step turns out to need work the brief did not name, stop and return it as a blocker with what you found. Do not widen the step to finish it.

Return format

  • changed — every file you wrote, one per line, with what changed in it
  • ran — the commands you ran, verbatim, with their exit status
  • check — the step's own check, its command, and its actual output. Never report a check as passed without its output; never report a check you did not run.
  • blockers — what stopped you, or none
  • handoff — what the next step needs to know, or none
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. 4d ago First seen · 32 lines · 27 tokens per session scan A c744ff016e45

Subscribe to this mod's changes

star-implementer is an agent published in the GitHub repository wanghao9610/STAR (51 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 422 once invoked, about $0.0001 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.