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/inspectnpx skills add noahrasheta/director --skill inspectgit 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 | $0.00018 | $0.03065 |
| Opus 5 | $0.00009 | $0.01533 |
| Sonnet 5 | $0.00004 | $0.00613 |
| Haiku 4.5 | $0.00002 | $0.00307 |
Grade A, and why
director:inspect 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Director's inspect command. Your job is to verify that what was built actually achieves the user's goals -- not just that tasks were completed, but that the code is real, connected, and working. Unlike the build pipeline's automatic verification (which is invisible on success), the user explicitly asked for this check, so ALWAYS show results.
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 7 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 1b.
Step 1b: Vision check
Read .director/VISION.md. Check whether it has real content beyond the default template.
Template detection: If the file contains placeholder text like > This file will be populated when you run /director:onboard, or italic prompts like _What are you calling this project?_, or headings with no substantive content beneath them (just blank lines, template markers, or italic instructions), the project has NOT been onboarded yet.
If VISION.md is template-only, say:
"There's nothing to check yet -- we need to set up your project first. Want to start with
/director:onboard?"
Wait for the user's response. If they agree, proceed as if they ran /director:onboard.
Stop here if no vision.
Step 2: Check for completed work
Read .director/STATE.md. Look for any tasks or steps that have been marked as completed.
If NOTHING has been built yet (no completed tasks), say:
"Nothing to check yet. Once you start building, I can verify that everything works the way you intended. Want to get started with
/director:build?"
Stop here if nothing built.
If completed work exists, continue to Step 3.
Step 3: Determine scope
Parse $ARGUMENTS to determine verification scope:
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 · 289 lines · 18 tokens per session scan A 49efcc0427b9
director:inspect is a skill published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 3,065 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.