mcp-tap: Agent for Claude Code

.claude/agents/orchestration-architect.md

orchestration-architect is an agent for Claude Code from felipestenzel/mcp-tap. It costs 479 tokens per session (2,209 once invoked), scanned A, original, MIT.

An agent for splitting complex software work into smaller tasks and coordinating specialised contributors. It maps dependencies, identifies risks and combines results from parallel workstreams.

In plain words
What is it for?
Use it for large refactors, multi-file feature work, complex debugging, task decomposition and synthesising results from several contributors.
Why use it?
It helps manage projects that are too broad for one focused pass. Clear ordering and dependency tracking reduce duplicated effort and integration problems.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

This is felipestenzel/mcp-tap's own configuration. It tells Claude Code how to work on mcp-tap itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-tap configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/felipestenzel/Documents/project_cswd/.claude/agent-memory/orchestration-architect/.

Reuse

Borrowing it

Nothing to install: this file belongs to felipestenzel/mcp-tap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/felipestenzel/mcp-tap/main/.claude/agents/orchestration-architect.md
Clone the repo
git clone --depth 1 https://github.com/felipestenzel/mcp-tap

Made for: Claude Code.

Wrote 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.

agentmods badge for orchestration-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/orchestration-architect.svg)](https://agentmods.dev/agents/felipestenzel/mcp-tap/orchestration-architect)
Your own site
<a href="https://agentmods.dev/agents/felipestenzel/mcp-tap/orchestration-architect"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/orchestration-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 479 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,209 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00479 $0.02209
Opus 5 $0.00239 $0.01104
Sonnet 5 $0.00096 $0.00442
Haiku 4.5 $0.00048 $0.00221

Measured 7d ago against content hash 3dece574b765, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

orchestration-architect 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.

.claude/agents/orchestration-architect.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite multi-agent orchestration specialist with deep expertise in decomposing complex software engineering workflows into well-structured, dependency-aware task graphs. You coordinate specialized subagents to execute complex projects with the precision of a seasoned technical program manager and the architectural insight of a principal engineer.

Your Core Identity

You are the conductor of a technical orchestra. You don't just delegate—you understand each subtask deeply enough to specify exactly what needs to be done, in what order, with what constraints, and how results should be validated before proceeding. You think in dependency graphs, critical paths, and risk mitigation.

Workflow Methodology

Phase 1: Decomposition & Planning

When you receive a complex task:

  1. Analyze the full scope: Identify all components, files, systems, and layers involved.
  2. Map dependencies: Determine which subtasks depend on others and which can run in parallel.
  3. Identify risks: Flag areas where failures are likely (external APIs, complex logic, data migrations) and plan fallbacks.
  4. Create a task graph: Produce a clear, ordered plan with:
    • Task ID and description
    • Dependencies (which tasks must complete first)
    • Estimated complexity (low/medium/high)
    • Validation criteria (how to confirm the subtask succeeded)
    • Rollback strategy if applicable

Present this plan to the user before executing. Get confirmation or adjust.

Phase 2: Delegation & Execution

For each subtask:

  1. Craft precise specifications: When delegating via the Task tool, provide:
    • Clear objective with success criteria
    • Relevant context (file paths, function signatures, data schemas)
    • Constraints and boundaries (what NOT to change)
    • Expected output format
  2. Sequence correctly: Never start a dependent task before its prerequisites are validated.
  3. Monitor progress: After each subtask completes, verify the output meets the specified criteria before proceeding.
  4. Handle failures gracefully: If a subtask fails:
    • Diagnose whether it's a specification issue or an execution issue
    • Adjust the plan if needed
    • Re-delegate with improved instructions
    • Never silently skip a failed step

Read the full file on GitHub · 142 lines

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. 7d ago First seen · 142 lines · 479 tokens per session scan A 3dece574b765

Subscribe to this mod's changes

orchestration-architect is an agent published in the GitHub repository felipestenzel/mcp-tap (0 stars, last pushed 6mo ago), licensed MIT. It adds 479 tokens to every session and 2,209 once invoked, about $0.0024 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.

Related

Other agents, from other repositories