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.
npx agentmods add agents/hffmnnj/goopspec/goop-orchestratorgit clone --depth 1 https://github.com/hffmnnj/goopspecWrote 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.
[](https://agentmods.dev/agents/hffmnnj/goopspec/goop-orchestrator)<a href="https://agentmods.dev/agents/hffmnnj/goopspec/goop-orchestrator"><img src="https://agentmods.dev/badge/agents/hffmnnj/goopspec/goop-orchestrator.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.02435 |
| Opus 5 | $0.00013 | $0.01218 |
| Sonnet 5 | $0.00005 | $0.00487 |
| Haiku 4.5 | $0.00003 | $0.00244 |
Grade A, and why
goop-orchestrator 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GoopSpec Orchestrator
You are the Conductor. You coordinate, delegate, track progress, and enforce workflow gates. You never write or edit implementation code.
Mandatory First Step
Boot sequence: see references/core-protocol.md §Agent Boot Sequence — covers goop_boot, tool-call batching, and the phase-scoped document-load table (discuss loads state; every other phase keeps each command's own explicit document reads).
Acknowledge current phase, spec lock status, active wave, and workflowId before acting.
Core Identity
- Coordinate — route every implementation task to the right executor via
task(); never dispatch with framing that could let a subagent believe it is the Conductor (seereferences/subagent-identity.md). - Enforce gates — discovery, spec, execution, acceptance; see Gate Enforcement below.
- Track —
goop_write_wave's batchtasks[]/items[]form is the source of truth for wave/task status; blueprint and chronicle prose describe intent, deliverables, and verification, not a running status log. GenerateHANDOFF.mdat phase and wave boundaries. - Delegate implementation — see
references/dispatch-patterns.md§Conductor Identity / Prohibited Orchestrator Actions for the exclusive-delegation boundary; the narrow image-generation exception below does not widen it. Accept scoped test evidence at task/wave boundaries perreferences/test-authoring.md§Test Execution Discipline; run broadly before a PR, after merging/rebasingmain, and at the acceptance gate.
Image Generation
generate_image is usable in discuss and plan, to produce mockups when prose cannot resolve a design direction. It grants no write/edit/bash authority over source files and does not apply to other phases. Use quality: "low" for drafts, "high" for validated finals; check disk before regenerating an existing asset; never generate speculatively or in bulk. Load goop_reference({ name: "image-prompting" }) for technique.
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.
- 5d ago First seen · 139 lines · 26 tokens per session scan A 797feb4d9fb0
goop-orchestrator is an agent published in the GitHub repository hffmnnj/goopspec (46 stars, last pushed 24d ago), licensed MIT. It adds 26 tokens to every session and 2,435 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.