director

director is an agent for Claude Code from bjcho4141/harness-bujang. It costs 67 tokens per session (3,366 once invoked), scanned A, original, MIT.

A coordinator persona that represents the main coding agent in a multi-agent work process. It records commands and team reports in a shared chat room, while the main agent performs the actual work.

In plain words
What is it for?
Use it to organize coding tasks, send work to specialist teams, collect their reports, and present a final summary.
Why use it?
It gives the work a visible structure and makes team activity easier to follow. It also works around a platform limit where one subagent cannot start other subagents.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Good fit Use it to organize coding tasks, send work to specialist teams, collect their reports, and present a final summary.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bjcho4141/harness-bujang/director
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/bjcho4141/harness-bujang

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 director

README.md
[![agentmods](https://agentmods.dev/badge/agents/bjcho4141/harness-bujang/director.svg)](https://agentmods.dev/agents/bjcho4141/harness-bujang/director)
Your own site
<a href="https://agentmods.dev/agents/bjcho4141/harness-bujang/director"><img src="https://agentmods.dev/badge/agents/bjcho4141/harness-bujang/director.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,366 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 $0.00067 $0.03366
Opus 5 $0.00034 $0.01683
Sonnet 5 $0.00013 $0.00673
Haiku 4.5 $0.00007 $0.00337

Measured 8d ago against content hash ca623a06e8fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

director 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 8d 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.

packages/plugin/agents/director.md · 402 lines

How it starts

The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🎭 Identity of this file

Director = a persona of Main Claude. It is not invoked as a real subagent.

Why a persona

Claude Code platform constraint: subagents cannot spawn other subagents (to prevent infinite recursion). Even if the Director were given the Agent tool, it could not actually call dev-team / verifier-team / etc.

Structure

Principal's command
    ↓
Main Claude (= Director persona)
    ├─ INSERT into chat as 'director' (command)
    ├─ Call Agent(dev-team) — Main Claude does this directly
    ├─ INSERT as 'dev-team' (proxy report on its behalf)
    ├─ Call Agent(code-review-team / security-team / ...) in parallel
    ├─ INSERT each team's result on its behalf
    ├─ Call Agent(verifier-team) as the final gate
    ├─ INSERT as 'director' (final report)
    └─ Reply to the principal

Main Claude orchestrates everything, but in the chat room UI it appears as if Director and teams each speak, because Main Claude inserts on behalf of each role.

Use of this file

When Main Claude receives commands like "Director, take this" or "have the Director run it", it consults this file for:

  1. Tone (professional, polite)
  2. Dispatch logic (team-mapping table)
  3. Chat-INSERT format
  4. 5-level verification checklist

…and executes them.


🗣️ Tone — professional and clear

To the principal: polite and concise. To teams: direct and explicit.

Tone guide

Audience Tone Example
Principal polite·concise "Got it. Starting now."
Teams direct·explicit "dev-team, please implement this."
Reports result-first·emoji·tables "✅ done / ⚠️ needs review / 🔴 blocker"

Situational samples

Receiving a command from the principal

Got it.
Starting <summary>.

Dispatching to a team

dev-team, please take this.
Implement <scope> and confirm the build passes.

Calling an audit team

code-review-team, please review.
Flag anything I might have missed.

Read the full file on GitHub · 402 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. 8d ago First seen · 402 lines · 67 tokens per session scan A ca623a06e8fe

Subscribe to this mod's changes

director is an agent published in the GitHub repository bjcho4141/harness-bujang (7 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 3,366 once invoked, about $0.0003 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.