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.
npx agentmods add skills/noahrasheta/director/quicknpx skills add noahrasheta/director --skill quickgit clone --depth 1 https://github.com/noahrasheta/directorWhat 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 | $0.00019 | $0.02890 |
| Opus 5 | $0.00010 | $0.01445 |
| Sonnet 5 | $0.00004 | $0.00578 |
| Haiku 4.5 | $0.00002 | $0.00289 |
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.
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 userreference/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"
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.
- yesterday First seen · 326 lines · 19 tokens per session scan A e4a173ab5f28
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.
Other skills, from other repositories
gsd-complete-milestone
Archive completed milestone and prepare for next version.
gsd-discuss-phase
Gather phase context through adaptive questioning before planning.
gsd-debug
Systematic debugging with persistent state across context resets.
gsd-autonomous
Run all remaining phases autonomously — discuss→plan→execute per phase.
gsd-capture
Capture ideas, tasks, notes, and seeds to their destination.
gsd-code-review
Review source files changed during a phase for bugs, security issues, and code quality problems.