What is mcp-task-orchestrator CLAUDE.md?

Project instructions for an MCP server that coordinates development tasks among specialized AI roles and stores persistent memory. MCP is a standard connection between an AI assistant and external tools.

For working on the MCP Task Orchestrator and following its integration rules, architecture guidance, and failure-recovery procedure.

They define what to do when the task orchestrator fails, including checking the connection, running diagnostics, reading logs, and assigning repair work. This provides a required troubleshooting process for the project.

How EchoingVesper/mcp-task-orchestrator configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to EchoingVesper/mcp-task-orchestrator. 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/EchoingVesper/mcp-task-orchestrator/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/EchoingVesper/mcp-task-orchestrator

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/echoingvesper/mcp-task-orchestrator/claude-md/github.svg)](https://agentmods.dev/instructions/echoingvesper/mcp-task-orchestrator/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/echoingvesper/mcp-task-orchestrator/claude-md"><img src="https://agentmods.dev/badge/instructions/echoingvesper/mcp-task-orchestrator/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/echoingvesper/mcp-task-orchestrator/claude-md"><img src="https://agentmods.dev/badge/instructions/echoingvesper/mcp-task-orchestrator/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,416 This file is loaded in full into every session.

When invoked 3,416 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.03416	$0.03416
Opus 5.5	$0.01366	$0.01366
Sonnet 5.5	$0.00683	$0.00683
Haiku 4.5	$0.00342	$0.00342

Measured 2mo ago against content hash 3bfe4cad8299, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

mcp-task-orchestrator CLAUDE.md scanned grade B 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

tail -n 50 ~/.claude/logs/mcp-*.log 2>/dev/null || echo "No logs found"

CLAUDE.md · 437 lines

How it starts

The opening of the file, as written. The whole thing — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

MCP Tools Integration

@/home/aya/.claude/mcp-tools-core.md

Available MCP servers provide search, development, and automation capabilities. See user memory for detailed usage patterns.

Project Overview

The MCP Task Orchestrator is a Model Context Protocol server that provides intelligent task orchestration, specialized AI roles, and persistent memory for AI-assisted development. It follows Clean Architecture and Domain-Driven Design principles with a complete layered structure.

Critical Directives

CRITICAL: Task Orchestrator Failure Protocol

If the MCP Task Orchestrator ever fails to function:

STOP - Do not proceed with current task or "work around" the issue

DIAGNOSE - Immediately spawn a diagnostic agent to identify the issue:

# Check MCP connection
claude mcp list 2>/dev/null | grep task-orchestrator || echo "Not connected"

# Run health check
python tools/diagnostics/health_check.py

# Check server logs
tail -n 50 ~/.claude/logs/mcp-*.log 2>/dev/null || echo "No logs found"

FIX - Spawn a dedicated fix agent with these priorities:
- Follow detailed procedures in PRPs/protocols/orchestrator-fix-protocol.md
- Fix known issues in the orchestrator code
- Restart the MCP server if needed: claude mcp restart task-orchestrator
- If changes were made to server code: pip install -e . && claude mcp restart task-orchestrator
- Update documentation if Claude Code restart is required
VERIFY - Test the fix with orchestrator_health_check tool
RESUME - Only continue original task after verification

Never say "the orchestrator isn't working, let's continue without it"

CRITICAL: Git Commit After Every Task

After completing ANY development task:

ALWAYS review changes: git status && git diff

COMMIT with descriptive message:

git add -A
git commit -m "type(scope): description"
# Examples:
# fix(orchestrator): resolve connection timeout issue
# feat(prp): add orchestrator integration to PRP process
# docs(claude): add critical failure protocol

Include orchestrator task ID in commit if applicable
Never leave uncommitted changes between tasks

Read the full file on GitHub · 437 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.

2mo ago First seen · 437 lines · 3,416 tokens per session scan B 3bfe4cad8299

Subscribe to this mod's changes

mcp-task-orchestrator CLAUDE.md is an instructions file published in the GitHub repository EchoingVesper/mcp-task-orchestrator (28 stars, last pushed 1y ago), licensed MIT. It adds 3,416 tokens to every session, about $0.0137 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Memory and context ai-agents ai-automation ai-framework ai-orchestration ai-tools anthropic

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

mcp-task-orchestrator: Instructions file for Claude Code