director:quick

A skill for handling small, focused code changes through a short workflow. It checks the project setup, reads the requested task, and passes suitable work to the builder.

In plain words
What is it for?
Use it for narrowly scoped requests such as changing a button colour, editing one file, or making another small code adjustment.
Why use it?
It avoids the overhead of a full planning process for minor changes while still checking whether the task fits the quick workflow.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/noahrasheta/director/quick
Any agent
npx skills add noahrasheta/director --skill quick
Clone the repo
git clone --depth 1 https://github.com/noahrasheta/director

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,890 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00019 $0.02890
Opus 5 $0.00010 $0.01445
Sonnet 5 $0.00004 $0.00578
Haiku 4.5 $0.00002 $0.00289

Measured yesterday against content hash e4a173ab5f28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

director:quick 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 yesterday.

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.

skills/quick/SKILL.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Director's quick command. Your job is to execute small, focused changes without the full planning workflow. The user describes what they want, you assess complexity, and if it's quick-appropriate, you hand it off to the builder with assembled context.

Read these references for tone and terminology:

  • reference/plain-language-guide.md -- how to communicate with the user
  • reference/terminology.md -- words to use and avoid

Follow all 8 steps below IN ORDER.


Step 1: Init check

Check if .director/ exists.

If it does NOT exist, run the initialization script silently:

!`bash ${CLAUDE_PLUGIN_ROOT}/scripts/init-director.sh`

Continue to Step 2.

Quick mode does NOT require a vision or gameplan. It works on bare .director/ projects -- no onboarding needed.

Step 2: Check for a task description

Look at $ARGUMENTS. If empty (the user ran /director:quick with no description), say:

"What would you like to change? Try something like: /director:quick \"change the button color to blue\""

Stop here if no arguments.

Step 3: Analyze complexity (scope-based detection)

Read the user's request in $ARGUMENTS and assess whether it is appropriate for quick mode. This is scope-based detection -- you are looking at what the request INVOLVES, not counting files.

Escalation triggers (suggest blueprint)

If the request matches ANY of these patterns, it may be too complex for quick mode:

  • Multiple features in one request: "add login AND a dashboard", "set up payments and notifications"
  • Architectural language: "redesign", "refactor", "overhaul", "restructure", "rearchitect", "rewrite"
  • Cross-cutting concerns: "change how all pages handle errors", "update the authentication everywhere", "add logging to every endpoint"
  • New system-level capabilities: "add authentication", "set up payments", "add a database", "build an API layer"
  • Multi-system changes: "update the API and the frontend", "change the database and all the pages that use it"

Read the full file on GitHub · 326 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. yesterday First seen · 326 lines · 19 tokens per session scan A e4a173ab5f28

Subscribe to this mod's changes

director:quick is a skill published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 2,890 once invoked, about $0.0001 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.