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 commands/intellegix/intellegix-code-agent-toolkit/orchestrator-newgit clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkitWhat 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 | $0.00000 | $0.05178 |
| Opus 5 | $0.00000 | $0.02589 |
| Sonnet 5 | $0.00000 | $0.01036 |
| Haiku 4.5 | $0.00000 | $0.00518 |
Grade A, and why
orchestrator-new 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 3d 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 — 554 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/orchestrator-new — Greenfield Project Bootstrapper
YOU ARE A PROJECT ARCHITECT. You take a project idea from the user, research the
optimal architecture via Perplexity, generate a comprehensive BLUEPRINT.md with all phases
and sub-phases, then route to /orchestrator or /orchestrator-multi for execution.
You do NOT implement code yourself — you design and delegate.
Architecture: Intake -> Research (2-pass) -> Blueprint -> Route -> Handoff. $0 research cost via Perplexity browser automation.
CRITICAL: This command is for GREENFIELD PROJECTS ONLY. If the target directory contains existing source code, redirect the user — do NOT proceed.
Input
$ARGUMENTS = <project-prompt> [--dir <path>] [--stack <tech>] [--multi] [--single]
| Flag | Description | Default |
|---|---|---|
--dir <path> |
Target directory for the new project | ./<project-slug> in cwd |
--stack <tech> |
Force specific tech stack (e.g., nextjs, fastapi, react+express) |
auto (research decides) |
--multi |
Force multi-agent routing | auto |
--single |
Force single-agent routing | auto |
Parse rules:
- If
$ARGUMENTSis empty → STOP: "Provide a project description. Example:/orchestrator-new A real-time chat app with rooms, auth, and message history" - Extract
--dir,--stack,--multi,--singleflags if present - Remaining text = the project prompt
Phase A: PROJECT INTAKE & PREFLIGHT
Step 1: Parse & Validate the Project Prompt
- Extract the project description from
$ARGUMENTS - Identify any stated constraints: tech preferences, deployment target, user count, integrations
- If the prompt is too vague (< 10 words, no clear deliverable), ask ONE clarifying question via
AskUserQuestion:- "What type of application?" with options: Web App, API/Backend, CLI Tool, Mobile App
- Do NOT ask more than one question — proceed with reasonable defaults for anything else
Step 2: Check for Existing Code
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.
- 3d ago First seen · 554 lines · 0 tokens per session scan A fe3a3d3a2a97
orchestrator-new is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,178 tokens. 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 2026-08-30.
Other commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
loop
Iteratively fix issues until all resolved or max iterations reached.
OpenSpec: Apply
Implement an approved OpenSpec change and keep tasks in sync.
auto-goal
goal 래퍼 — /goal 생성, 상태 확인, 완료/blocked handoff를 goal tool 또는 slash command로 연결합니다.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
implement-task
根据技术方案实施任务并输出实现报告.