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 skills/linhh29/skill_mas/init_skillnpx skills add linhh29/Skill_MAS --skill init_skillgit clone --depth 1 https://github.com/linhh29/Skill_MASWhat 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 | $0.00039 | $0.00551 |
| Opus 5 | $0.00019 | $0.00275 |
| Sonnet 5 | $0.00008 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
unified_meta_agent_skill 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 2d 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
1. Task Decomposition Module (The "What")
Core Objective: Analyze the user query and break it down into a logical blueprint.
- Intent & Scope Analysis: Understand the macro objective, identify core requirements, and define the boundaries of the task.
- Sub-task Breakdown: Decompose the high-level request into a set of discrete, manageable, and logically cohesive sub-tasks.
- Logical Dependency Mapping: Identify the business-logic relationships between sub-tasks (e.g., prerequisite, parallel, or iterative). Note: This focuses on logical order, not system dataflow.
- Success Criteria: Define clear objective outcomes for each sub-task to ensure evaluability.
2. Agent Engineering Module (The "Who")
Core Objective: Design specialized sub-agents tailored for the sub-tasks defined in Stage 1.
- Role Profiling: Assign a unique identity and specialized role to each sub-agent based on its target sub-task.
- Instruction Design: Draft precise system prompts/instructions. Define the agent's specific goals, behavioral boundaries, and output expectations.
- Input Context Framing: Specify what contextual information this agent requires from the user or the global task to begin its work.
3. Workflow & Orchestration Module (The "How")
Core Objective: Wire the distinct agents from Stage 2 into a functional, executable Multi-Agent System (MAS).
- Architectural Topology: You can design the optimal MAS architecture (e.g., Sequential Pipeline, Router-based, Hierarchical, or Blackboard) based on Stage 1's logical dependencies. For those complex but important sub-tasks, you can design localized different topology design using the instantiated agents. For example, you can define a iterative loops for those sub-tasks that need a cycle check to ensure high quality. Or you can call the same agent multiple times to generate diverse outputs and give all of thems to the following sub-agents.
- Dataflow & State Management: Define the exact I/O mapping. Specify how the output schema of one agent transforms into the input payload/prompt of downstream agents. Determine how global context (memory/state) is maintained.
- Executable Generation: Output the final orchestration logic/code structure that binds the agents, tools, and dataflow into a ready-to-run system.
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.
- 2d ago First seen · 33 lines · 39 tokens per session scan A 76109ecaea55
unified_meta_agent_skill is a skill published in the GitHub repository linhh29/Skill_MAS (43 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 551 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 2026-08-30.
Other skills, from other repositories
review-findings
Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and prepares for re-verification. Delegates to the Forja (Dev) agent.
feature-spec
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
implement-feature
Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to the Forja (Dev) agent.
orchestrate
This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.
dagu
Authors, validates, and troubleshoots Dagu DAG definitions and assists with Dagu CLI operations. Use when creating or debugging DAG YAML, choosing Dagu commands, or inspecting and managing DAGs and runs from the CLI.
recipe-decompose
Decomposes Linear issues or requirement documents into the fewest implementation-ready value units, then registers the approved tasks in Linear. Use when "decompose", "break down tasks", "split into tasks", "task breakdown", or "create Linear issues from requirements".