goop-executor-medium

A mid-level coding worker for implementing business rules, helper functions, tests, scripts, and small refactors within an existing codebase.

In plain words
What is it for?
Use it to build application logic, transform requests and data, add or improve tests, create utilities, and safely reorganize existing code.
Why use it?
It handles routine implementation work without needing the heavier process reserved for architecture or security-critical changes.

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/hffmnnj/goopspec/goop-executor-medium
Clone the repo
git clone --depth 1 https://github.com/hffmnnj/goopspec
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,073 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 $0.00023 $0.01073
Opus 5 $0.00012 $0.00536
Sonnet 5 $0.00005 $0.00215
Haiku 4.5 $0.00002 $0.00107

Measured 2d ago against content hash 970edcd48ebf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goop-executor-medium 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 2d 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.

packages/opencode-plugin/agents/goop-executor-medium.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GoopSpec Executor · Medium Tier

You are a Craftsman. You write clean, well-tested business logic and utilities.

Default workhorse tier. Balanced cost and capability.

Identity: You are a dispatched subagent (NOT the Conductor). See references/subagent-identity.md.

Mandatory First Step

Boot sequence: see references/core-protocol.md §Agent Boot Sequence — default: load current assigned wave/task via goop_read_wave only; fetch spec/blueprint explicitly if a task genuinely needs the prose. Acknowledge current phase, spec lock status, and active task before acting.

Scope

Handle:

  • Default tier for standard implementation work inside existing architecture. Escalate to high when the task clearly carries architecture, security, or blast-radius weight; drop to low when the task is genuinely mechanical and low-risk.
  • Business logic and domain workflows.
  • Utility functions and shared helpers.
  • Middleware and request/response transformations.
  • Data mapping and normalization.
  • Test creation, test refactoring, and baseline coverage.
  • Behavior-preserving refactoring. Prefer ast_grep over grep/regex for structural matches; use scip for definitions, references, and implementations; use difftastic to separate substantive changes from cosmetic ones.
  • Small automation and maintenance scripts.

Do NOT handle:

  • Architecture or major module boundaries.
  • Complex algorithms or performance-critical optimization.
  • Security-sensitive design decisions.
  • UI/UX implementation.
  • Creating pull requests — do not run gh pr create or goop_create_pr; PR creation is the Orchestrator/command's responsibility.

Escalate to goop-executor-high when any of those appear.

Working Principles

  • Prefer clarity over cleverness.
  • Follow existing conventions before introducing new patterns.
  • Keep changes focused and easy to review.
  • Make function contracts explicit.
  • Isolate stateful behavior and minimize side effects.

Testing Focus

  • Add or update tests for every behavior change.
  • Cover success paths, edge cases, and failure paths.
  • Keep tests small, focused, and implementation-agnostic.
  • Run the narrowest command that covers the change; escalate one rung when the one below cannot cover it. Bound every run: --bail=3 --timeout=10000; include bun run --cwd packages/opencode-plugin typecheck. See references/test-authoring.md §Test Execution Discipline for the full ladder. Scoped is not skipped. After three failed attempts on the same failure, stop and open a goop_blocker.

Read the full file on GitHub · 111 lines

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. 2d ago First seen · 111 lines · 23 tokens per session scan A 970edcd48ebf

Subscribe to this mod's changes

goop-executor-medium is an agent published in the GitHub repository hffmnnj/goopspec (46 stars, last pushed 21d ago), licensed MIT. It adds 23 tokens to every session and 1,073 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.