ryantlee25-droid/spectrum-protocol

A coordination protocol for parallel AI agents in Claude Code. 6 Color-coded agents. Frozen contracts. File ownership. Adversarial review. No dependencies — copy three files and run.

5Stars on the repository
15Mods indexed here, across every type
6mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

blues

01

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Work planner agent. Breaks tasks into structured PLAN.md with actionable steps, file ownership, test criteria, and verified references. Produces plans developers or workers can execute without follow-up questions.

not rated 5 6mo ago A 41 tokens original MIT

browns

02

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Retrospective agent. Reads spectrum artifacts (HOOK.md, debriefs, SEAM-CHECK.md, PAX-PLAN.md) and drafts LESSONS.md capturing what worked, what failed, and recommendations. user: "write up lessons from this spectrum run" assistant: uses Brown to aggregate artifacts into a structured LESSONS.md draft user: "draft the…

not rated 5 6mo ago A 123 tokens original MIT

coppers

03

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Git agent for commits, branches, and PRs/MRs on GitHub and GitLab. Smart commit messages, risk-tiered confirmation, file sensitivity filtering, convention learning.

not rated 5 6mo ago A 38 tokens original MIT

golds

04

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Lightweight parallel dispatcher. Writes SPLIT.md (file ownership), drops workers in worktrees, runs post-merge quality gate. Invoke for 3+ independent tasks or when the user says 'drop workers' / 'run parallel'.

not rated 5 6mo ago A 50 tokens original MIT

grays-run

05

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Mechanical test runner (Haiku tier). Auto-detects pytest, jest, vitest, playwright. Runs tests, reports pass/fail counts. Does NOT diagnose failures — if tests fail, Gold escalates to grays (Sonnet) for diagnosis. user: (Gold spawns after Howler completion) assistant: detects framework, runs tests, reports PASS/FAIL…

not rated 5 6mo ago A 87 tokens original MIT

grays

06

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Multi-framework test runner agent. Auto-detects pytest, jest, vitest, go test. Runs tests with coverage, generates missing tests using batch-generate-validate loops, reports failures with diagnosis.

not rated 5 6mo ago A 44 tokens original MIT

helldivers

07

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Product research and problem identification agent. Validates that a problem is real, significant, and worth solving before solution exploration. Produces a structured Problem Brief grounded in evidence-based discovery frameworks. user: "what problems should we focus on for our dev tools product?" assistant: uses…

not rated 5 6mo ago A 219 tokens original MIT

howlers

08

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Parallel implementation agent (also called 'worker'). Executes a scoped task in an isolated worktree with strict file ownership. Spawned by Gold during parallel execution.

not rated 5 6mo ago A 34 tokens original MIT

obsidians

09

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Post-merge spec compliance verifier. Reads PLAN.md acceptance criteria and verifies the merged codebase satisfies them. Produces SENTINEL-REPORT.md with per-criterion PASS/PARTIAL/FAIL verdicts. user: "did we build what we planned?" assistant: uses Obsidian to verify merged code against PLAN.md acceptance criteria…

not rated 5 6mo ago A 115 tokens original MIT

oranges

10

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Root cause debugging agent. Uses minimize-then-localize methodology, multi-signal evidence collection, and causal chain construction. Handles runtime exceptions, failing tests, type errors, and silent failures.

not rated 5 6mo ago A 41 tokens original MIT

politicos

11

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Adversarial reviewer for CONTRACT.md and MANIFEST.md. Challenges Gold's decomposition before freeze — finds ownership gaps, contract ambiguities, and decomposition flaws. Runs in Phase 1.5 (The Passage) before Howlers are dropped. user: Gold has written MANIFEST.md and CONTRACT.md and wants them reviewed before…

not rated 5 6mo ago A 131 tokens original MIT

primus

12

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Product strategy and management agent for PRDs, prioritization, roadmaps, and market analysis. Invoke when the user wants to think through what to build, why, and in what order — not how to build it technically. user: "help me write a PRD for the new reporting feature" assistant: uses product-strategy-partner to draft…

not rated 5 6mo ago A 223 tokens original MIT

violets

13

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Behavioral spec agent. Produces DESIGN.md — a detailed API contract, schema definition, or component hierarchy spec that Howlers use as ground truth during implementation. Invoke before muster when the spectrum involves shared interfaces, database schemas, or cross-Howler API contracts. user: "we need a design spec…

not rated 5 6mo ago A 185 tokens original MIT

whites

14

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Pre-PR code review agent. Uses tiered verification (reasoning certificates + batched tool calls) for speed. Produces structured Blocker/Warning/Suggestion/Inquiry reports with verified findings only.

not rated 5 6mo ago A 44 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: