goop-execute

goop-execute is a command for Claude Code from hffmnnj/goopspec. It costs 13 tokens per session (1,309 once invoked), scanned A, original, MIT.

A command that carries out a prepared GoopSpec implementation plan in waves, where each wave is a group of related tasks. It assigns tasks to specialized coding agents according to their complexity and risk.

In plain words
What is it for?
Use it to implement a locked GoopSpec plan, including ordinary coding, interface work, and architecture-sensitive or security-sensitive tasks.
Why use it?
It keeps implementation tied to an approved specification and blueprint. It also provides checkpoints so work starts only after the required planning steps are complete.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: agent in frontmatter.

Good fit Use it to implement a locked GoopSpec plan, including ordinary coding, interface work, and architecture-sensitive or security-sensitive tasks.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/hffmnnj/goopspec/goop-execute
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.

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

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 goop-execute

README.md
[![agentmods](https://agentmods.dev/badge/commands/hffmnnj/goopspec/goop-execute/github.svg)](https://agentmods.dev/commands/hffmnnj/goopspec/goop-execute)
Your own site
<a href="https://agentmods.dev/commands/hffmnnj/goopspec/goop-execute"><img src="https://agentmods.dev/badge/commands/hffmnnj/goopspec/goop-execute/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 goop-execute

Your own site · 80×15
<a href="https://agentmods.dev/commands/hffmnnj/goopspec/goop-execute"><img src="https://agentmods.dev/badge/commands/hffmnnj/goopspec/goop-execute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,309 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 $0.00013 $0.01309
Opus 5.5 $0.00005 $0.00524
Sonnet 5.5 $0.00003 $0.00262
Haiku 4.5 $0.00001 $0.00131

Measured 1mo ago against content hash 470b012f31c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

goop-execute 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 1mo 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/commands/goop-execute.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/goop-execute

Implement the blueprint one wave at a time. The orchestrator delegates all implementation to executor agents.

Gate check

Call goop_state({ action: "get" }). If specLocked is not true or no wave rows exist — check via goop_read_wave({ workflow_id }) returning at least one wave (not a 'no waves' message) — return BLOCKED with:

Run /goop-plan first.

Load references

goop_reference({ name: "dispatch-patterns" })
goop_reference({ name: "core-protocol" })

Steps

  1. Read goop_read_db({ doc_types: ["spec", "blueprint", "chronicle"] }) for narrative context and goop_read_wave({ workflow_id }) for wave/task context; read PROJECT_KNOWLEDGE_BASE.md.
  2. For each wave:
    • Delegate tasks to the right executor tier via task():
      • goop-executor-low for mechanical/pattern-following edits; escalate if hidden complexity.
      • goop-executor-medium for standard implementation work — the default tier when a task isn't clearly mechanical or complex/critical.
      • goop-executor-high for architecture-sensitive or security-critical work — use when genuinely warranted.
      • goop-executor-frontend-low for UI mechanical tasks; escalate if hidden complexity.
      • goop-executor-frontend-medium for standard UI component work — the default frontend tier when UI work isn't clearly mechanical or design/architectural.
      • goop-executor-frontend-high for deep design or UI-architecture work — use when genuinely warranted.
    • Use sequential dispatch for shared files; parallel dispatch for independent tasks.
    • Require every task to return STATUS, SUMMARY, ARTIFACTS, VERIFICATION, NEXT.
  3. Apply the four-rule deviation system from phase-gates. Log every deviation to ADL.md via goop_adl.
  4. Before dispatching a wave, call goop_state({ action: "update-wave", currentWave: N, totalWaves: M }) to record that Wave N is in progress. currentWave is 1-based; 0 means no wave has started.
  5. After every task in a wave completes, run the wave verification gate before the wave can be marked complete:
    • Dispatch goop-wave-verifier scoped to that wave — one wave per dispatch; the role is execute-phase and inspect-only (see agents/goop-wave-verifier.md).
    • The verifier records a verification row per task via goop_write_wave({ wave_number: N, verifications: [...] }) and never implements fixes.
    • On gaps: dispatch the correctly tiered executor to remediate, then re-dispatch goop-wave-verifier for that wave to re-verify the remediated tasks.
    • Bound the remediation cycle with the three-strikes convention in references/test-authoring.md §Test Execution Discipline: after three failed attempts on the same gap, open a blocker via goop_blocker and stop; do not loop.
    • The wave is complete when its rows satisfy the runtime gate: verification rows persist forever (never deleted or edited), and the gate reads the latest row per check_name — at least one check present, and every check's latest row non-fail. A later pass or explicit skip for the same check supersedes that check's own prior fail; it does not resolve a different check's unresolved fail (isWaveVerified in src/features/enforcement/verifier-stage.ts). The runtime enforces the boundary: goop_write_wave rejects a complete-status transition without it.
  6. If Atomic PRs = Yes: after the wave verification gate passes, open a PR for the verified wave against the previous branch (Wave N → Wave N-1; Wave 1 → main) via gh pr create or goop_create_pr. Do not wait for it to merge. Then create the Wave N+1 branch from the current wave's branch and continue. Show the PR URL in the checkpoint.
  7. Save a checkpoint at wave boundaries.

Read the full file on GitHub · 79 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. 1mo ago First seen · 79 lines · 13 tokens per session scan A 470b012f31c1

Subscribe to this mod's changes

goop-execute is a command published in the GitHub repository hffmnnj/goopspec (51 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 1,309 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 2026-08-30.