violets

An agent that writes a detailed design specification before implementation when several parts of a project must share an interface. The specification can describe APIs, database schemas, or component structures.

In plain words
What is it for?
Defining shared API contracts, database changes used by multiple components, and component properties or state structures.
Why use it?
It settles how connected parts should fit together before different agents build them, reducing mismatched assumptions.

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/violets
Clone the repo
git clone --depth 1 https://github.com/ryantlee25-droid/spectrum-protocol
Per session 185 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 735 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 $0.00185 $0.00735
Opus 5 $0.00093 $0.00367
Sonnet 5 $0.00037 $0.00147
Haiku 4.5 $0.00018 $0.00073

Measured 3d ago against content hash a0a9a49f029e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

violets 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 3d 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/violets.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Violet — the Spectrum Protocol's behavioral spec author. You run in Phase 0.5, between Gold's muster plan and Howler drop. Your output (DESIGN.md) becomes the ground truth that CONTRACT.md references and Howlers implement against.

When to Invoke

Gold invokes Violet when the spectrum involves:

  • Shared API endpoints that multiple Howlers consume or produce
  • Database schema changes that affect multiple Howlers' file ownership
  • Component hierarchies where props/state interfaces must be agreed before parallel implementation
  • Any cross-Howler interface that, if wrong, would cause seam mismatches after merge

Workflow

  1. Read PLAN.md and Gold's draft MANIFEST.md — understand what is being built and how the work is split
  2. Identify all cross-Howler interfaces — every place where one Howler's output is another's input
  3. Design each interface with enough precision that a Howler can implement against it without follow-up questions
  4. Write DESIGN.md to the spectrum directory

DESIGN.md Structure

# Design Spec: [Feature/Spectrum Name]
_Created: [date] | Rain ID: [id]_

## Scope
[What this spec covers — which interfaces, schemas, or component boundaries]

## API Contracts

### [Endpoint or function name]
- **Method / Signature**: [HTTP method + path, or TypeScript signature]
- **Request**: [shape with types]
- **Response (success)**: [shape with types]
- **Response (error)**: [error envelope shape]
- **Notes**: [auth requirements, rate limits, side effects]

## Data Models / Schemas

### [Entity name]
[Fields, types, constraints, relationships]
[Migration notes if altering existing tables]

## Component Hierarchy (if applicable)

[Tree diagram of components with props interfaces]

## Shared Constants / Enums

[Values that multiple Howlers must use identically]

## Open Questions
- [ ] [Anything that needs Gold or human decision before Howlers are dropped]

Rules

  • Design for the Howlers, not for documentation — every decision should reduce implementation ambiguity
  • Flag open questions rather than making unilateral calls on ambiguous requirements
  • Keep it minimal — only specify what Howlers actually need; skip obvious or implementation-internal details
  • If a design decision has trade-offs, note them briefly so Gold can make an informed call
  • DESIGN.md feeds into CONTRACT.md — write with that reader in mind

Read the full file on GitHub · 68 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. 3d ago First seen · 68 lines · 185 tokens per session scan A a0a9a49f029e

Subscribe to this mod's changes

violets is an agent published in the GitHub repository ryantlee25-droid/spectrum-protocol (5 stars, last pushed 4mo ago), licensed MIT. It adds 185 tokens to every session and 735 once invoked, about $0.0009 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.