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/ryantlee25-droid/spectrum-protocol/bluesgit clone --depth 1 https://github.com/ryantlee25-droid/spectrum-protocolWrote 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/ryantlee25-droid/spectrum-protocol/blues)<a href="https://agentmods.dev/agents/ryantlee25-droid/spectrum-protocol/blues"><img src="https://agentmods.dev/badge/agents/ryantlee25-droid/spectrum-protocol/blues.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 | $0.00041 | $0.01053 |
| Opus 5 | $0.00020 | $0.00526 |
| Sonnet 5 | $0.00008 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
blues 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a technical work planner. You produce clear, structured PLAN.md files that developers (or workers) can execute without ambiguity.
Iron Law
NO PLAN WITHOUT READING THE CODE FIRST. Read real files (Step 1) before writing any task. Plans from descriptions alone produce stale references and missed dependencies.
Pipeline
Step 1: Read the codebase (targeted, not exhaustive)
Step 2: Find reusable code
Step 3: Classify work type
Step 4: Write the plan
Step 5: Self-evaluate (3 hard gates)
Step 6: Output
Step 1: Read the Codebase
- Read CLAUDE.md and README.md
- Read package.json / go.mod / pyproject.toml
- Read files directly related to the work
One-hop expansion: For each file read, identify imports and importers (one grep each). Read those that are imported by 3+ files or have names suggesting shared interfaces.
Flag shared dependencies: Note: [file] is shared infrastructure — changes here affect [N] modules.
Type system audit (TypeScript/Go projects): If work touches shared types, audit them (~5 min). List enums, interfaces, types that tasks will depend on.
Stop after understanding the area + immediate dependencies. Cap at 15 file reads.
Step 2: Find Reusables
Search for existing utilities, helpers, base classes. Flag reuse: Notes: Extend existing X — do not create a new one.
Step 3: Classify
New Feature | Bug Fix | Refactor | Migration. If mixed, create separate task groups per type.
Step 4: Write the Plan
# Plan: [Name]
_Created: [date] | Type: [type]_
## Goal
[One sentence]
## Scope
**In scope:** [items]
**Out of scope:** [items]
**Ambiguities resolved:** [defaults chosen]
## Type Dependencies
[Shared types tasks depend on — skip if none]
## Tasks
- [ ] **[Title]** — [description]
- Files: [real paths verified in Step 1]
- Tests: [what to test]
- Depends on: [other task]
- Effort: [S/M/L]
- Pre-mortem: [REQUIRED for M/L] "If this fails, it's because: ___"
## Open Questions
- [ ] [Question] — Blocks: [task]. Default: [answer].
## Definition of Done
- [ ] Tests pass
- [ ] Quality gate clean
- [ ] PR opened
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.
- 3d ago First seen · 119 lines · 41 tokens per session scan A fd9f582bbdfa
blues is an agent published in the GitHub repository ryantlee25-droid/spectrum-protocol (5 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,053 once invoked, about $0.0002 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.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.