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 skills add noahrasheta/director --skill helpgit clone --depth 1 https://github.com/noahrasheta/directorWrote 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.
[](https://agentmods.dev/skills/noahrasheta/director/help)<a href="https://agentmods.dev/skills/noahrasheta/director/help"><img src="https://agentmods.dev/badge/skills/noahrasheta/director/help/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.
<a href="https://agentmods.dev/skills/noahrasheta/director/help"><img src="https://agentmods.dev/badge/skills/noahrasheta/director/help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00029 | $0.02812 |
| Opus 5.5 | $0.00012 | $0.01125 |
| Sonnet 5.5 | $0.00006 | $0.00562 |
| Haiku 4.5 | $0.00003 | $0.00281 |
Grade A, and why
director:help 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Director Help
!cat .director/STATE.md 2>/dev/null || echo "NO_PROJECT"
Check the output above. If .director/STATE.md was found and contains project information, show a mini-status header before the command list. Parse the STATE.md content to find the project name (from the first heading or "Project" field), the current goal, current step, and current task. Format it as:
You're working on [project name]. Currently on [current goal] -- [current step/task summary].
If the output was "NO_PROJECT" (no .director/ exists), show this welcome instead:
Welcome to Director! Here's what you can do:
Check for topic-specific help
Look at $ARGUMENTS. If the user provided an argument, check whether it matches one of the command names below (case-insensitive, with or without the /director: prefix):
Recognized command names: onboard, blueprint, build, quick, undo, inspect, status, resume, refresh, brainstorm, pivot, idea, ideas, help
- If
$ARGUMENTSmatches a command name: Show the topic-specific help for that command (see the Topic-Specific Help section below). Do NOT show the full command list. - If
$ARGUMENTSdoes not match a command name: Show the full command list below. - If
$ARGUMENTSis empty: Show the full command list below.
Commands
Blueprint (Plan Your Project)
| Command | What it does | Example |
|---|---|---|
/director:onboard |
Set up a new project or map an existing one | /director:onboard |
/director:blueprint |
Create, view, or update your gameplan | /director:blueprint "add payment processing" |
Build (Make Progress)
| Command | What it does | Example |
|---|---|---|
/director:build |
Work on the next ready task | /director:build |
/director:quick "..." |
Fast change without full planning | /director:quick "change the button color to blue" |
/director:undo |
Go back to before the last task | /director:undo |
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.
- 1mo ago First seen · 268 lines · 29 tokens per session scan A 023bda4cdcd3
director:help is a skill published in the GitHub repository noahrasheta/director (2 stars, last pushed 8mo ago), licensed MIT. It adds 29 tokens to every session and 2,812 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
gsd-surface
Toggle which skills are surfaced — apply a profile, list, or disable a cluster without reinstall.
gsd-capture
Capture ideas, tasks, notes, and seeds to their destination.
gsd-profile-user
Generate developer behavioral profile and create Claude-discoverable artifacts.
gsd-ns-manage
config workspace | workstreams thread update ship inbox.
gsd-fast
Execute a trivial task inline — no subagents, no planning overhead.
gsd-ns-ideate
exploration capture | explore sketch spike spec capture.