# Command Reference This document mirrors `src/index.ts` command registration and is the canonical CLI reference. Last sync: 2026-06-14. ## Quick examples ```bash fable-agent run "Review API security risks" fable-agent session start "ship launch plan" fable-agent skills list --tag security fable-agent pai status fable-agent fable5 stack "refactor module" --enable-plinius fable-agent fusion run "summarize RFC" --openrouter fable-agent plinius godmode "improve explanation quality" ``` ## Top-level commands `fable-agent [subcommand] [options]` | Command | Primary purpose | |---|---| | `run` | Execute full agent loop | | `session` | Session lifecycle | | `skills` | Skill registry ops | | `state` | Knowledge state / stats view | | `pai` | PAI/bridge operations | | `status` | Runtime surface summary | | `workflow` | Load workflow JSON | | `benchmark` | Run/view benchmark metrics | | `cost` | Cost/usage reporting | | `exa` | Exa search utilities | | `demo` | Demo mode | | `learned` | Summaries of learned material | | `familiar` | Note capture and health graph | | `pai-pi` | PI integration mode | | `daemon` | Long-running mode queue/monitor | | `fable5` | Upgraded execution stack | | `fusion` | Multi-panel execution | | `generate` | Media generation | | `plinius` | Fable 5 diagnostics and upgrade tools | --- ## Command matrix ### `run` - `run ` - Options: - `-l, --loop `: feedback loop iterations - `-w, --workflow `: workflow definition ID - `-s, --skill `: explicit skill override - `-c, --compound `: compound run count ### `session` - `session start ` - `session resume ` - `session list` - `session inspect ` ### `skills` - `skills list` - `-t, --tag ` - `skills create ` - `-s, --steps ` - `-t, --tags ` - `skills inspect ` - `skills evolve ` - `skills sync` - `skills sharpen` ### `state` - `state` - `-t, --tag ` - `--stats` ### `status` - `status` - Displays command availability, env bootstrap, and runtime wiring summary. ### `pai` - `pai status` - `pai telos` - `-s, --section ` - `pai proxy ` - `-m, --model ` (default `fi-groq`) - `-t, --temperature ` - `-s, --system ` - `pai sync` - `pai dream` - `-c, --cycle ` - `--dry-run` - `pai cert` - `-t, --task ` - `-l, --loop ` - `--skip-proxy-check` - `pai bridge` - `pai memory` - `pai packs` - `pai report` - `pai run ` ### `workflow` - `workflow ` ### `benchmark` - `benchmark run` - `-b, --benchmark ` - `benchmark trend` - `-b, --benchmark ` - `benchmark list` ### `cost` - `cost report` - `-h, --hours ` ### `exa` - `exa search ` - `-n, --num-results ` - `-t, --type `: keyword|neural|auto - `--include-domains ` - `exa company ` - `exa sync` ### `demo` - `demo` - `-q, --query ` ### `learned` - `learned` - `-v, --verbose` ### `familiar` - `familiar capture ` - `-s, --source ` - `familiar process` - `familiar graph` - `familiar health` - `familiar briefing` ### `pai-pi` - `pai-pi status` - `pai-pi skills` - `pai-pi run ` - `-l, --loop ` ### `daemon` - `daemon start` - `-d, --detach` - `daemon stop` - `daemon status` - `daemon queue ` - `-p, --priority ` - `-t, --tags ` ### `fable5` - `fable5 status` - `fable5 route ` - `-d, --domain ` - `fable5 models` - `fable5 verify ` - `fable5 goal ` - `-i, --iterations ` - `-s, --min-score ` - `fable5 worktree [name]` - `fable5 state ` - `--add-fact ` - `--add-rule ` - `--add-failure ` - `--add-lesson ` - `--import` - `fable5 workflow ` - `-s, --subtasks ` - `-n, --max-iterations ` - `-p, --panel ` - `--category ` - `--intensity ` - `fable5 compound ` - `--skill ` - `fable5 chain ` - `--stages ` - `fable5 meta ` - `--stages ` - `fable5 teams ` - `--workers ` - `fable5 stack ` - `-p, --project ` - `--enable-worktrees` - `--enable-vision` - `--enable-workflows` - `--enable-fusion` - `--enable-plinius` - `fable5 rpc` - `-p, --port ` ### `fusion` - `fusion run ` - `-p, --panel ` - `-j, --judge ` - `--openrouter` - `fusion panels` ### `generate` - `generate image ` - `-m, --model ` (default `fal-ai/nano-banana-pro`) - `--aspect ` - `-r, --reference ` - `generate video ` - `-m, --model ` (default `alibaba/happy-horse/image-to-video`) - `-p, --prompt ` - `-d, --duration ` - `--720p` ### `plinius` - `plinius godmode ` - `-p, --panel ` - `-m, --mode ` - `--proxy` - `-v, --verbose` - `plinius ultra ` - `-o, --output ` - `plinius parseltongue ` - `-c, --category ` - `-i, --intensity ` - `plinius autotune ` - `-s, --scores ` - `plinius stm ` - `-m, --modules ` - `--max-length ` - `plinius refusal ` - `-m, --model ` - `-t, --task ` - `plinius observatory` - `-p, --provider ` - `-m, --model ` - `-t, --tag ` - `-l, --limit ` - `plinius liberation` - `--min-success ` - `plinius transparency ` - `-m, --model ` - `--save` ## Env and runtime references - Env bootstrap command: `loadEnv()`. - Env precedence: existing process env > `.env` values. - Files loaded from project root: - `.env` - `.env.` - `.env.local` - Proxy-sensitive commands: `pai proxy`, `pai cert`, `plinius godmode --proxy`. ## Parity checklist Before merging command-layer changes, verify: 1. `COMMANDS.md` includes each `.command(...)` addition/removal from `src/index.ts`. 2. New or changed flags are listed in this file. 3. `CONFIG.md` includes matching bootstrap/env/proxy updates when startup behavior changes. 4. A smoke command confirms the command parses in the shell: - `node dist/index.js --help` (or equivalent).