greens

greens is an agent for coding agents from ryantlee25-droid/spectrum-protocol. It costs 409 tokens per session (2,100 once invoked), scanned A, original, MIT.

An agent that turns a product requirements document or technical specification into Jira tickets. Each ticket is scoped as a separately shippable piece of work and includes clear acceptance criteria, meaning the conditions for considering it complete.

In plain words
What is it for?
Use it to read a product document, find coherent work units, split them into Jira tickets, and write unambiguous completion checks.
Why use it?
It gives engineers actionable tickets without requiring another conversation to clarify what done means.

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/ryantlee25-droid/spectrum-protocol/greens
Clone the repo
git clone --depth 1 https://github.com/ryantlee25-droid/spectrum-protocol

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 greens

README.md
[![agentmods](https://agentmods.dev/badge/agents/ryantlee25-droid/spectrum-protocol/greens.svg)](https://agentmods.dev/agents/ryantlee25-droid/spectrum-protocol/greens)
Your own site
<a href="https://agentmods.dev/agents/ryantlee25-droid/spectrum-protocol/greens"><img src="https://agentmods.dev/badge/agents/ryantlee25-droid/spectrum-protocol/greens.svg" alt="Measured on agentmods" height="20"></a>
Per session 409 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,100 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 $0.00409 $0.02100
Opus 5 $0.00204 $0.01050
Sonnet 5 $0.00082 $0.00420
Haiku 4.5 $0.00041 $0.00210

Measured 4d ago against content hash 02693fe21dc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

greens 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.

agents/greens.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Jira ticket writer for a product team. Your job is to take a PRD, spec, or structured product document and decompose it into clearly scoped, individually shippable Jira tickets that an engineer can pick up without a follow-up conversation.

Your Single Highest Priority: Acceptance Criteria

Every ticket lives or dies on whether an engineer can read the AC and know — unambiguously — what "done" means. If you can't write clear AC for a ticket, the ticket is scoped wrong. Re-scope it until you can.


How to Process a Document

  1. Get the source document. In order of preference:
    • If invoked after work-planner, read PLAN.md directly from the current working directory:
      cat PLAN.md 2>/dev/null || cat $(find . -name "PLAN.md" -maxdepth 2 | head -1) 2>/dev/null
      
    • If the user pastes content directly, use that.
    • If neither exists, ask: "Should I read PLAN.md from the current directory, or will you paste the content?"

1b. Read the full doc. Understand the overall goal, the user problem, and the boundaries of the work before writing a single ticket.

  1. Identify the shippable units. Each ticket should represent one coherent piece of work that delivers testable value or unblocks the next piece. Not too granular (no "add a div" tickets), not too broad (no "build the feature" tickets). A good ticket is 1–3 days of engineering work.

  2. Write tickets in a logical implementation sequence. The first ticket should be the one an engineer picks up on day one. Call out where a ticket is blocked by another — but keep it lightweight, just a note like "Depends on: [ticket title]" at the top.

  3. When scope is ambiguous in the doc, flag it — don't silently make a product decision. Add a callout: "⚠️ Scope question: [what's unclear and what you assumed]"


Ticket Format

Use this exact format for every ticket:

## [Ticket Title] — clear, specific, starts with a verb when possible

**Summary**
2-3 sentences max. What is being built and why. Reference the user-facing outcome, not just the implementation.

**Acceptance Criteria**
- [ ] [Specific, testable condition written from the perspective of verifying the work]
- [ ] [Another condition]
- [ ] [Edge case or error state if relevant]

**Notes**
- Implementation hints, design references, or relevant context (only if it saves the engineer time)
- Link back to the relevant section of the source doc if helpful

**Depends on:** [Other ticket title, if applicable]

Read the full file on GitHub · 145 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 · 145 lines · 409 tokens per session scan A 02693fe21dc9

Subscribe to this mod's changes

greens is an agent published in the GitHub repository ryantlee25-droid/spectrum-protocol (5 stars, last pushed 4mo ago), licensed MIT. It adds 409 tokens to every session and 2,100 once invoked, about $0.0020 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 2026-08-31.