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 skills add j4flmao/agent-skills --skill master-orchestratorgit clone --depth 1 https://github.com/j4flmao/agent-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/skills/j4flmao/agent-skills/master-orchestrator)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/master-orchestrator"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/master-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/j4flmao/agent-skills/master-orchestrator"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/master-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00113 | $0.14289 |
| Opus 5 | $0.00056 | $0.07144 |
| Sonnet 5 | $0.00023 | $0.02858 |
| Haiku 4.5 | $0.00011 | $0.01429 |
Grade A, and why
master-orchestrator scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
State: User asks about API client, curl command, HTTP request generation. How it starts
The opening of the file, as written. The whole thing — 1,557 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Master Orchestrator
Purpose
Inspect project state and route to the correct skill. This skill NEVER implements, debugs, or designs. It only routes.
Agent Protocol
Trigger
Exact user phrases: "start", "help me build", "initialize", "I want to build X", "where do I start", "what skill", "what should I do next", "begin", "let's start".
Input Context
- Working directory must be set to the project root.
- If no project root is detectable, ask the user: "Where is your project directory?"
Output Artifact
None. This skill produces no files. It emits a routing decision as text.
Response Format
The agent MUST output exactly one of the following templates. No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick. No explanations.
Template A — Route to a single skill:
Next skill: **{skill-name}**
Reason: {one sentence exactly}
Context: {key facts the next skill needs}
Template B — Route to multiple skills (sequential):
Next skills:
1. **{skill-name}** — {reason}
2. **{skill-name}** — {reason}
Template C — Need more information:
Need: {what you need from the user}
Options:
- {option 1}
- {option 2}
Completion Criteria
This skill is complete when:
- Project state has been checked (docs/, README, package manifests)
- Stack/language detected or asked
- A single next skill has been identified
- Output follows exactly one of the three templates above
- No implementation, debugging, or advice has been given
Max Response Length
3 lines maximum for routing. 6 lines maximum for "need more information."
Workflow
Step 1: Check Filesystem
Run these checks in order. Stop at the first match.
Test-Path -LiteralPath docs/brief*.md— brief existsTest-Path -LiteralPath docs/prd*.md— PRD existsTest-Path -LiteralPath docs/decisions/— ADRs existTest-Path -LiteralPath docs/specs/— tech specs existTest-Path -LiteralPath package.json— Node projectTest-Path -LiteralPath Cargo.toml— Rust projectTest-Path -LiteralPath go.mod— Go projectTest-Path -LiteralPath requirements.txtorpyproject.toml— Python projectTest-Path -LiteralPath pom.xmlorbuild.gradle— Java project
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/algorithms.md 445 KB
- references/architecture.md 449 KB
- references/best_practices.md 454 KB
- references/configuration.md 452 KB
- references/data_schemas.md 449 KB
- references/decision_matrices.md 462 KB
- references/master-orchestrator-advanced.md 12 KB
- references/master-orchestrator-fundamentals.md 11 KB
- references/orchestration-engine.md 2.7 KB
- references/orchestrator-registration.md 8.2 KB
- references/performance.md 447 KB
- references/phase-workflow.md 2.6 KB
- references/routing-decision-tree.md 11 KB
- references/skill-registry.md 3.0 KB
- references/skill-routing.md 2.1 KB
- references/troubleshooting.md 457 KB
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.
- 6d ago First seen · 1,557 lines · 113 tokens per session scan A 582b414d2feb
master-orchestrator is a skill published in the GitHub repository j4flmao/agent-skills (22 stars, last pushed 3d ago), licensed MIT. It adds 113 tokens to every session and 14,289 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
trigger-authoring-tasks
Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…