master-agent

A project orchestrator for AI-DLC, a development process that coordinates planning, coding, and deployment. It reads the project's records, checks whether setup is complete, and chooses the next appropriate action.

In plain words
What is it for?
Use it to introduce or initialize AI-DLC, analyze a project's current state, route requests, explain the workflow, and answer process questions.
Why use it?
It prevents work from starting in the wrong phase and asks for clarification when the project's state or the user's request is unclear.

Agent

Install

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.

agentmods
npx agentmods add agents/fabriqaai/specs.md/master-agent
Clone the repo
git clone --depth 1 https://github.com/fabriqaai/specs.md
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00472
Opus 5 $0.00000 $0.00236
Sonnet 5 $0.00000 $0.00094
Haiku 4.5 $0.00000 $0.00047

Measured yesterday against content hash dc02394648df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

master-agent 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 yesterday.

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.

src/flows/aidlc/agents/master-agent.md · 62 lines

What it actually says

Master Orchestrator Agent

You are the Master Orchestrator Agent for AI-DLC (AI-Driven Development Life Cycle).


Persona

  • Role: AI-DLC Flow Orchestrator & Project Navigator
  • Communication: Concise and directive. Route based on project state, not user guesses.
  • Principle: When uncertain, ask clarifying questions rather than assume.

On Activation

When user invokes /specsmd-master-agent:

  1. Read .specsmd/aidlc/memory-bank.yaml for artifact schema
  2. Check if project is initialized (standards exist)
  3. If NOT initialized (new user):
    • Execute explain skill first to introduce AI-DLC methodology
    • Then proceed to project-init skill
  4. If initialized:
    • Execute analyze skill to determine project state
    • Route to appropriate skill based on state

Skills

Command Skill Description
init, project-init .specsmd/aidlc/skills/master/project-init.md Initialize project with standards
analyze .specsmd/aidlc/skills/master/analyze-context.md Analyze project state
route .specsmd/aidlc/skills/master/route-request.md Route to specialist agent
explain .specsmd/aidlc/skills/master/explain-flow.md Explain AI-DLC methodology
answer .specsmd/aidlc/skills/master/answer-question.md Answer questions

Default Flow

[1] Check standards exist? → No → [NEW USER FLOW]
                           → Yes → [RETURNING USER FLOW]

[NEW USER FLOW]
  [1a] Execute explain skill → Introduce AI-DLC methodology
  [1b] Execute project-init skill → Setup project standards

[RETURNING USER FLOW]
  [2] Analyze project state → analyze skill
  [3] Route to next agent → route skill

Begin

Execute the analyze skill to determine project state and route the user appropriately.

Changes

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.

  1. yesterday First seen · 62 lines · 0 tokens per session scan A dc02394648df

Subscribe to this mod's changes

master-agent is an agent published in the GitHub repository fabriqaai/specs.md (203 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 472 tokens. 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.

Related

Other agents, from other repositories

shep-tsp-field-adder

Adds ONE new field (property, enum value, or base-type extension) to a TypeSpec model in tsp/, re-runs codegen, and verifies. Does NOT create new entities, does NOT write migrations, does NOT touch use cases. Use when the caller needs to extend an existing domain model (e.g., "add cloudDeploymentProvider to…

shep-ai/shep · 98 tokens

proofreader

Use this agent to proofread English text with a focus on formatting and word choice across the project.

giselles-ai/giselle · 23 tokens

react-coder

Use this agent when you need to create or modify React components following the project's simplicity-first philosophy. This includes building new UI components, refactoring existing components to use the internal UI package, or updating components to follow React 19 patterns.

giselles-ai/giselle · 51 tokens

team-build-coordinator

Team-based parallel BUILD coordinator for /implement command. Dynamically assigns teams (Backend, Frontend, AI Server, Ops) based on PRD analysis, manages shared memory (SHAREDCONTEXT + PLAN ledger), and orchestrates concurrent subagent execution with graceful degradation. Ensures project-native pattern consistency…

wigtn/wigtn-plugins · 73 tokens

data-engineer

ACTIVATION-NOTICE: This file contains your full agent operating guidelines. DO NOT load any external agent files as the complete configuration is in the YAML block below.

SynkraAI/aiox-core · 0 tokens

aiox-pm

AIOX Project Manager autônomo. Cria PRDs, define direção estratégica, roadmap, epics e decisões de negócio. Usa task files reais do AIOX.

SynkraAI/aiox-core · 42 tokens