A command workflow that chooses and coordinates software agents before carrying out a task. It first reads the project's orchestration rules, available agents, and their capability descriptions.

Use it to inspect an agent pool, compare agents with task requirements, and select, merge, or create agents for the work.

It removes the need to manually decide which agent should handle each part of a task. It also checks whether existing agents are a good match before combining them or creating a new one.

How shintaro-sprech/agent-orchestrator-template configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shintaro-sprech/agent-orchestrator-template. 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/shintaro-sprech/agent-orchestrator-template/main/.claude/commands/task.md

Clone the repo

git clone --depth 1 https://github.com/shintaro-sprech/agent-orchestrator-template

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/commands/shintaro-sprech/agent-orchestrator-template/task/github.svg)](https://agentmods.dev/commands/shintaro-sprech/agent-orchestrator-template/task)

Your own site

<a href="https://agentmods.dev/commands/shintaro-sprech/agent-orchestrator-template/task"><img src="https://agentmods.dev/badge/commands/shintaro-sprech/agent-orchestrator-template/task/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/commands/shintaro-sprech/agent-orchestrator-template/task"><img src="https://agentmods.dev/badge/commands/shintaro-sprech/agent-orchestrator-template/task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 516 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.

Model	Per session	Once invoked
Fable 5.1	$0.00010	$0.00516
Opus 5.5	$0.00004	$0.00206
Sonnet 5.5	$0.00002	$0.00103
Haiku 4.5	$0.00001	$0.00052

Measured 2mo ago against content hash 185e9ec72265, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task 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 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.

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/commands/task.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrated Task Execution

You MUST follow the orchestrator workflow before executing this task.

Step 1: Read Orchestrator

Read .claude/agents/orchestrator.md completely to understand the orchestration logic.

Step 2: Scan Agent Pool

Scan all existing agents:

.claude/agents/pool/specialized/ - Task-specific agents
.claude/agents/pool/integrated/ - Merged agents
.claude/agents/pool/elite/ - High-performing agents

For each agent found, read its definition (.md file).

Step 3: Read Skill Sheets

Read corresponding skill sheets from .claude/agents/manifests/ to understand:

Agent capabilities
Constraints
Usage metrics
Synergy hints

Step 4: Calculate Coverage

Compare task requirements against available agent capabilities:

List required skills for this task
Calculate match percentage for each agent
Identify potential synergies between agents

Step 5: Decision Matrix

Coverage Rate	Action
90%+	Use existing agent directly
60-90%	Create integrated agent by merging sources
Below 60%	Create new specialized agent

Step 6: Agent Creation (if needed)

If creating new/integrated agent:

Use .claude/agents/_template.md as base
Save agent definition to appropriate pool/ subdirectory
Create skill sheet in manifests/

Step 7: Execute Task

Execute the following task using the selected/created agent:

$ARGUMENTS

Step 8: Update Metrics

After task completion, update the agent's skill sheet in manifests/:

Increment usage_count
Update success_rate
Set last_used to today's date
Add entry to task_history

Step 9: Elite Promotion Check

If agent meets criteria (usage_count >= 5 AND success_rate >= 0.8):

Move agent from current location to pool/elite/
Update skill sheet tier: elite

Step 10: Report

Report:

Agent used (name, tier, location)
Action taken (used existing / created new / integrated)
Coverage achieved
Any agents created or promoted

Read the full file on GitHub · 79 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 · 79 lines · 10 tokens per session scan A 185e9ec72265

Subscribe to this mod's changes

task is a command published in the GitHub repository shintaro-sprech/agent-orchestrator-template (124 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 516 once invoked, about $0.0000 per session on Opus 5.5. 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.

Building agents Planning

task next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
taskshintaro-sprech/agent-orchestrator-template	Command	124	2mo ago	MIT	A	10	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

agent-orchestrator-template: Command for Claude Code