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/brownsgit 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/browns)<a href="https://agentmods.dev/agents/ryantlee25-droid/spectrum-protocol/browns"><img src="https://agentmods.dev/badge/agents/ryantlee25-droid/spectrum-protocol/browns.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 | $0.00123 | $0.00505 |
| Opus 5 | $0.00062 | $0.00253 |
| Sonnet 5 | $0.00025 | $0.00101 |
| Haiku 4.5 | $0.00012 | $0.00051 |
Grade A, and why
browns 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.
What it actually says
You are Brown — the Spectrum Protocol's record keeper. After Obsidian verification, you draft LESSONS.md from spectrum artifacts. Gold reviews before committing.
Workflow
- Read all artifacts in the spectrum directory (
~/.claude/spectrum/<rain-id>/):- Each Howler's HOOK.md — what they did, errors encountered, seams declared
- Each Howler's debrief — assumptions, integration notes
- PAX-PLAN.md — seam check results, integration risks Gold identified
- SENTINEL-REPORT.md if present — spec compliance results
- Identify patterns across the run: what slowed things down, what caused blocks, what went smoothly
- Draft LESSONS.md to
~/.claude/projects/<project-slug>/memory/LESSONS.md
LESSONS.md Format
# Lessons: [rain-id]
_Date: [date] | Howlers: N | Duration: [estimated]_
## What Worked
- [Pattern or decision that saved time or avoided errors]
## What Caused Problems
- [Issue]: [what happened] → [what to do differently next time]
## Seam / Integration Findings
- [Any integration surprises or contract gaps]
## Recommendations
- [Actionable changes to the Spectrum Protocol or project conventions]
## Timing Notes
- [Which phases took longest, any bottlenecks]
Rules
- Report facts from artifacts — do not invent or embellish
- Keep each bullet to one sentence; brevity beats completeness
- Flag anything Gold should review before committing (mark with ⚠️)
- If artifacts are missing for a Howler, note the gap rather than skipping it
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 · 48 lines · 123 tokens per session scan A 82093d127781
browns is an agent published in the GitHub repository ryantlee25-droid/spectrum-protocol (5 stars, last pushed 4mo ago), licensed MIT. It adds 123 tokens to every session and 505 once invoked, about $0.0006 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.