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/statusnpx skills add noahrasheta/director --skill statusgit 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 | $0.00012 | $0.02487 |
| Opus 5 | $0.00006 | $0.01243 |
| Sonnet 5 | $0.00002 | $0.00497 |
| Haiku 4.5 | $0.00001 | $0.00249 |
Grade A, and why
director:status 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Director's status command. Show the user where their project stands with a clear, visual progress display. This is the user's dashboard -- make it immediately useful.
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 6 steps below IN ORDER.
Dynamic Context
<project_state>
!cat .director/STATE.md 2>/dev/null || echo "NO_PROJECT"
</project_state>
<project_config>
!cat .director/config.json 2>/dev/null || echo "{}"
</project_config>
Step 1: Check for a project
Look at the injected <project_state> above.
If it contains "NO_PROJECT" (no .director/ folder exists), say:
"No project set up yet. Director helps you plan and build software projects step by step. Want to get started with
/director:onboard? I'll ask a few questions about what you're building."
Stop here if no project.
Step 2: Check for arguments
Check $ARGUMENTS:
- If it contains "cost" or "detailed": set an internal flag for detailed cost view and skip to Step 6 after completing Step 3.
- Otherwise: show the default progress view (Steps 3-5).
Step 3: Calculate progress from file system (ground truth)
This is critical. The file system is the source of truth for progress -- STATE.md may be stale.
3a: Scan the file system
- List all directories in
.director/goals/. Each directory is a goal. - For each goal directory, list all subdirectories (each is a step).
- For each step directory, list all
.mdfiles in itstasks/subdirectory. - Count:
- Total tasks per step: All
.mdfiles (including.done.mdfiles) intasks/. Note: each.done.mdfile corresponds to a completed task -- do NOT double-count the original.mdfile and the.done.mdfile. Count unique task names. A task that has both01-setup.mdand01-setup.done.mdis ONE task (completed). A task that only has01-setup.mdis ONE task (pending). - Completed tasks per step: Files ending in
.done.mdintasks/. - Pending tasks per step: Total minus completed.
- Total tasks per step: All
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 · 260 lines · 12 tokens per session scan A 4043ca23c39c
director:status is a skill published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 2,487 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.