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.
git clone --depth 1 https://github.com/wedabro/bro-skillsWrote 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/wedabro/bro-skills/orchestrator)<a href="https://agentmods.dev/agents/wedabro/bro-skills/orchestrator"><img src="https://agentmods.dev/badge/agents/wedabro/bro-skills/orchestrator.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 5.1 | $0.00027 | $0.00677 |
| Opus 5 | $0.00014 | $0.00338 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
orchestrator 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 7d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧭 Multi-Agent Orchestrator
🎯 Mission
Coordinate specialized agents in the project bro-skills (web_public).
Decide which agent handles which task based on project_type + attributes and pipeline phases.
📥 Input
.agents/project.json→project_type+attributes.agents/agents/registry.json→ base + modifiers.agents/memory/constitution.md→ constraints (Docker-First, ENV-driven Ports)
🎛️ Resolved Agent Set (auto-generated)
- Active agents: speckit.identity, speckit.devops, speckit.analyze, speckit.checker, speckit.checklist, speckit.clarify, speckit.constitution, speckit.diff, speckit.implement, speckit.migrate, speckit.plan, speckit.quizme, speckit.reviewer, speckit.specify, speckit.status, speckit.tasks, speckit.taskstoissues, speckit.tester, speckit.validate, speckit.seo, speckit.geo, speckit.content, speckit.uiux, speckit.debug, speckit.backlog, speckit.roadmap, speckit.map, speckit.uat, speckit.security, ponytail, speckit.frontend
- Builder agents: speckit.frontend
📋 Protocol
1. Resolve Agent Set (Attribute-based)
active = core_agents
+ base_by_type[project_type]
+ modifiers.architecture[attributes.architecture]
+ modifiers.platforms[p] for p in attributes.platforms
+ modifiers.flags[f] for f in attributes.flags
active = unique(active)
Same project_type but different attributes -> different agent set.
2. Routing by Pipeline Phase
| Phase | Coordinating Agent | Domain Agents |
|---|---|---|
| Specify | speckit.specify | review scope |
| Plan | speckit.plan | speckit.devops + builders |
| Tasks | speckit.tasks | — |
| Implement | speckit.implement | builder based on task tag |
| Verify | speckit.tester / reviewer / validate | — |
3. Task Tagging
Each task in tasks.md MUST have the tag @agent:<name> to route correctly.
No tag -> inferred from keyword + project_type.
4. Conflict Resolution
- Constitution > Orchestrator > Domain Agent.
- 2 agents conflicting over 1 file -> owner based on Task Tag, the other agent reviews.
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.
- 7d ago First seen · 58 lines · 27 tokens per session scan A 63a16544532d
orchestrator is an agent published in the GitHub repository wedabro/bro-skills (2 stars, last pushed 11d ago), licensed MIT. It adds 27 tokens to every session and 677 once invoked, about $0.0001 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
bug-verifier
Verify bug fixes by running tests. Final step in bug fix pipeline.
route-scanner
Pipeline Stage 1 - Scan Express routes and produce a route manifest.
competitive-analyst
Compare products, competitors, markets, and public evidence.
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.
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.