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/ideanpx skills add noahrasheta/director --skill ideagit 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 | $0.00015 | $0.00883 |
| Opus 5 | $0.00008 | $0.00441 |
| Sonnet 5 | $0.00003 | $0.00177 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
director:idea 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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Director's idea command. Your job is to capture ideas instantly so the user doesn't lose them. Zero friction -- save and confirm, nothing more.
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 4 steps below IN ORDER.
Step 1: Check for Director project
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.
Step 2: Check for an idea
Look at $ARGUMENTS. If empty (the user ran /director:idea with no description), say:
"What's your idea? Try: /director:idea "add dark mode support""
Stop here if no arguments.
Step 3: Capture the idea (newest-first insertion)
Read the current contents of .director/IDEAS.md.
Insert the new idea AFTER the header block and BEFORE any existing ideas. The header block consists of the # Ideas heading and the italic description line that starts with _Captured ideas.
Insertion mechanic:
- Read the full file content.
- Find the line that starts with
_Captured ideas(the italic description line). This is the anchor point. - Insert the new idea on the NEXT line after the description line, pushing all existing ideas down.
- If there is no blank line between the description and the first existing idea, add one before the new idea entry.
- Write the updated file back.
New idea format:
- **[YYYY-MM-DD HH:MM]** -- [the idea text from $ARGUMENTS]
Use the current date and time for the timestamp.
IMPORTANT: Capture the idea text EXACTLY as the user typed it. Do not reformat, summarize, edit, add punctuation, capitalize, or change the text in any way. If they typed "maybe add a search bar idk" then save exactly "maybe add a search bar idk".
Save Progress
After the idea is written to IDEAS.md, save progress by committing the change:
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.
- 2d ago First seen · 102 lines · 15 tokens per session scan A 2e40886b714f
director:idea is a skill published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 883 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-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.
gsd-config
Configure GSD settings — workflow toggles, advanced knobs, integrations, and model profile.