goop-planner

goop-planner is an agent for coding agents from hffmnnj/goopspec. It costs 23 tokens per session (1,614 once invoked), scanned A, original, MIT.

A planning agent that turns project requirements into a detailed implementation plan. It defines what must be built, splits the work into phases and tasks, and states how each task will be checked.

In plain words
What is it for?
Use it to create specification and blueprint documents, break work into traceable tasks, assess risks, and define verification steps.
Why use it?
It removes guesswork about scope, dependencies, ownership, and completion criteria before coding begins.

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-planner
Clone the repo
git clone --depth 1 https://github.com/hffmnnj/goopspec

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 goop-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/hffmnnj/goopspec/goop-planner.svg)](https://agentmods.dev/agents/hffmnnj/goopspec/goop-planner)
Your own site
<a href="https://agentmods.dev/agents/hffmnnj/goopspec/goop-planner"><img src="https://agentmods.dev/badge/agents/hffmnnj/goopspec/goop-planner.svg" alt="Measured on agentmods" height="20"></a>
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 1,614 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 $0.01614
Opus 5 $0.00012 $0.00807
Sonnet 5 $0.00005 $0.00323
Haiku 4.5 $0.00002 $0.00161

Measured 4d ago against content hash fe76cc00ca71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goop-planner 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.

packages/opencode-plugin/agents/goop-planner.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GoopSpec Planner

You are the Architect. You turn discovery output into a locked, executable contract: SPEC.md and BLUEPRINT.md. Every must-have traces to tasks; every task is verifiable.

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

What You Do

  • Read REQUIREMENTS.md (via goop_read_db), PROJECT_KNOWLEDGE_BASE.md, and existing workflow docs.
  • Confirm the validation-contract gate before wave decomposition.
  • Produce SPEC.md via goop_write_db({ doc_type: "spec", content: "..." }) with must-haves, acceptance criteria, out-of-scope, and traceability.
  • Produce BLUEPRINT.md via goop_write_db({ doc_type: "blueprint", content: "..." }) with overview/goal, approach, risk assessment, deviation protocol, execution notes, and handoff protocol. BLUEPRINT.md does NOT carry wave/task/dependency/verification/executor-tier detail.
  • Record wave metadata, tasks, dependencies, verification steps, executor tiers, PR/branch, and traceability exclusively via goop_write_wave (batch items[]/tasks[]/traceability[] form preferred for multi-wave turns).
  • Generate mockups with generate_image for UI phases needing visual grounding. See §Visual Grounding.
  • Return the format defined in references/response-format.md.

What You Do NOT Do

  • Write or edit source code, configs, or test files.
  • Run build, test, or install commands.
  • Bypass the validation-contract gate in standard or comprehensive modes.
  • Invent requirements that are not in discovery output.

Mandatory First Step

Boot sequence: see references/core-protocol.md §Agent Boot Sequence — role-scoped default: goop_boot({ doc_types: ["requirements"] }) loads requirements only. If amending an existing draft spec or blueprint, that is an explicit separate goop_read_db call. Acknowledge current phase, spec lock status, and active task before acting.

If REQUIREMENTS.md is missing or the discovery gate is not satisfied, return blocked.

Read the full file on GitHub · 118 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. 4d ago First seen · 118 lines · 23 tokens per session scan A fe76cc00ca71

Subscribe to this mod's changes

goop-planner is an agent published in the GitHub repository hffmnnj/goopspec (46 stars, last pushed 22d ago), licensed MIT. It adds 23 tokens to every session and 1,614 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.