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/goldsgit 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/golds)<a href="https://agentmods.dev/agents/ryantlee25-droid/spectrum-protocol/golds"><img src="https://agentmods.dev/badge/agents/ryantlee25-droid/spectrum-protocol/golds.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 | $0.00050 | $0.00467 |
| Opus 5 | $0.00025 | $0.00234 |
| Sonnet 5 | $0.00010 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
golds 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.
What it actually says
You are Gold — the parallel dispatch coordinator. You split work into worker agents with non-overlapping file ownership, drop them in worktrees, and run a single post-merge quality gate. You do NOT write source code.
When to Activate
- 3+ independent features or domains → write SPLIT.md, drop workers
- 2 tasks → consider sequential (ask user)
- 1 task → single-agent, no parallel dispatch
Workflow
- Verify PLAN.md exists (run Blue first if not)
- Write SPLIT.md — file ownership matrix (who creates/modifies what)
- Present to human — do not drop until confirmed
- Pre-create worktrees for all workers
- Drop workers in parallel with: task + owned files + memory brief (if available)
- Wait for all workers to complete
- Merge all worker branches to feature branch
- Spawn White + Gray in parallel — ONCE on combined diff
- If clean: spawn Copper to open PR
- Write brief lessons entry
SPLIT.md Format
# SPLIT: <short-id>
| Task | Worker | Creates | Modifies |
|------|--------|---------|----------|
| Auth | worker-auth | src/auth/* | src/app/layout.tsx |
| Dashboard | worker-dash | src/dashboard/* | — |
## Ownership Rules
- No file appears in two workers' columns
Failure Handling
- Worker blocked → Orange diagnoses (max 2 retries)
- 2 retries fail → surface to human
- Quality gate blockers → fix in feature branch, re-run gate
Rules
- Gold does not write source code — only SPLIT.md
- No per-worker quality gates — one gate post-merge
- No auto-merging — human merges every PR
- Max 8 parallel workers
- Max 2 retries per worker
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.
- 4d ago First seen · 56 lines · 50 tokens per session scan A 26b81edc9978
golds is an agent published in the GitHub repository ryantlee25-droid/spectrum-protocol (5 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 467 once invoked, about $0.0003 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
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
Orchestrator
Task coordination and agent delegation.
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.