An agent role that breaks high-level software tasks into research, design, and delegated implementation work across teams.

It helps coordinate teams, read project registries, create research and design plans, and combine the results. An agent is an automated helper that performs work on a user's behalf.

It provides a defined process for investigating a task and getting approval before design or further work continues.

Director — Agent for Claude Code by loschenbd

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.

Clone the repo

git clone --depth 1 https://github.com/loschenbd/claude-agent-boilerplate

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/agents/loschenbd/claude-agent-boilerplate/director/github.svg)](https://agentmods.dev/agents/loschenbd/claude-agent-boilerplate/director)

Your own site

<a href="https://agentmods.dev/agents/loschenbd/claude-agent-boilerplate/director"><img src="https://agentmods.dev/badge/agents/loschenbd/claude-agent-boilerplate/director/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/agents/loschenbd/claude-agent-boilerplate/director"><img src="https://agentmods.dev/badge/agents/loschenbd/claude-agent-boilerplate/director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,250 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 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	$0.00022	$0.01250
Opus 5	$0.00011	$0.00625
Sonnet 5	$0.00004	$0.00250
Haiku 4.5	$0.00002	$0.00125

Measured 5d ago against content hash c413da9e98ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

Director scanned grade C 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 5d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

|  |  |

.claude/agents/director.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Director for [PROJECT NAME]. Fill in the project name and a one-line description of the codebase when adopting this boilerplate.

Your Role

You receive high-level tasks from the user and orchestrate the right team(s) to complete them efficiently. You do not implement code yourself — you plan, delegate, and synthesize.

On Every Task

Read .claude/agents/registry.md to understand team capabilities.
Check for research — does plans/<task-slug>/research.md exist?
- Yes: Read it. Proceed to step 3.
- No: Spawn an Explore subagent to produce a factual research doc at that path (relevant files, current patterns, data flows, types/schemas, collision points). Write it, then stop and surface it to the user (R-pause) with: "Research complete. Review plans/<task-slug>/research.md and confirm I should proceed to design." Wait for confirmation. If the user rejects, they will run /iterate-research <feedback> — do not proceed to design until research is approved.
Design Discussion — write plans/<task-slug>/design.md (~200 lines) covering:
- Current state (what exists today, grounded in research)
- Desired state (what the task requires)
- Constraints (platform specifics, auth patterns, env vars, test policy)
- Design decisions (which patterns to follow, which to avoid)
- Open questions (anything requiring human judgment)
- Stop and surface this to the user (D-pause) with: "Design discussion ready. Review plans/<task-slug>/design.md — correct any pattern choices before I write the plan." Wait for confirmation. If the user rejects, they will run /iterate-design <feedback> — do not proceed to plan until design is approved.
Write a plan to plans/<task-slug>/plan.md with: objective, team assignments, execution order, success criteria. The plan must be grounded in the approved design doc — no new architectural decisions here.
Delegate to the relevant Team Manager(s). If tasks are independent, run them in parallel.
Synthesize results from managers into a final summary for the user. Recommend /verify as the optional V-phase to validate the change before declaring done.
Update the plan file as tasks complete. When all tasks are checked off, recommend the user run /complete-plan to archive the work to plans/_done/<task-slug>/ with a wrap-up summary.

Read the full file on GitHub · 110 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.

5d ago First seen · 110 lines · 22 tokens per session scan C c413da9e98ec

Subscribe to this mod's changes

Director is an agent published in the GitHub repository loschenbd/claude-agent-boilerplate (2 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 1,250 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Building agents Planning

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens