This is the ONLY output format Skill

Agent-First CLI Design

CLIs in this system are agent-first, human-distant-second. Every command returns structured JSON that an agent can parse, act on, and follow. Humans are welcome to pipe through jq.

Core Principles

1. JSON always

Every command returns JSON. No plain text. No tables. No color codes. Agents parse JSON; they don't parse prose.

# This is the ONLY output format
mycli status
# → { "ok": true, "command": "mycli status", "result": {...}, "next_actions": [...] }

No --json flag. No --human flag. JSON is the default and only format.

2. HATEOAS — every response tells you what to do next

Every response includes next_actions — an array of command templates the agent can run next. Templates use standard POSIX/docopt placeholder syntax:

<placeholder> — required argument
[--flag <value>] — optional flag with value
[--flag] — optional boolean flag
No params field — literal command (run as-is)
params present — template (agent fills placeholders)
params.*.value — pre-filled from context (agent can override)
params.*.default — value if omitted
params.*.enum — valid choices

{
  "ok": true,
  "command": "mycli send pipeline/video.download",
  "result": {
    "event_id": "01KHF98SKZ7RE6HC2BH8PW2HB2",
    "status": "accepted"
  },
  "next_actions": [
    {
      "command": "mycli run <run-id>",
      "description": "Check run status for this event",
      "params": {
        "run-id": { "value": "01KHF98SKZ7RE6HC2BH8PW2HB2", "description": "Run ID (ULID)" }
      }
    },
    {
      "command": "mycli logs <source> [--lines <lines>] [--grep <text>] [--follow]",
      "description": "View worker logs",
      "params": {
        "source": { "enum": ["worker", "errors", "server"], "default": "worker" }
      }
    },
    {
      "command": "mycli status",
      "description": "Check system health"
    }
  ]
}

next_actions are contextual — they change based on what just happened. A failed command suggests different next steps than a successful one. Templates are the agent's affordances — they show what's parameterizable, what values are valid, and what the current context pre-fills.

3. Self-documenting command tree

Agents discover commands via two paths: the root command (JSON tree) and --help (Effect CLI auto-generated). Both must be useful.

Root command (no args) returns the full command tree as JSON:

{
  "ok": true,
  "command": "mycli",
  "result": {
    "description": "MyCLI — description of this tool",
    "health": { "server": {...}, "worker": {...} },
    "commands": [
      { "name": "send", "description": "Send event to backend", "usage": "mycli send <event> -d '<json>'" },
      { "name": "status", "description": "System status", "usage": "mycli status" },
      { "name": "gateway", "description": "Gateway operations", "usage": "mycli gateway status" }
    ]
  },
  "next_actions": [...]
}

--help output is auto-generated by Effect CLI from Command.withDescription(). Every subcommand must have a description — agents always call --help and a bare command list with no descriptions is useless.

// Bad: agents see a blank command list
const status = Command.make("status", {}, () => ...)

// Good: agents see what each command does
const status = Command.make("status", {}, () => ...).pipe(
  Command.withDescription("Active sessions, queue depths, health")
)

4. Context-protecting output

Agents have finite context windows. CLI output must not blow them up.

Rules:

Terse by default — minimum viable output
Auto-truncate large outputs (logs, lists) at a reasonable limit
When truncated, include a file path to the full output
Never dump raw logs, full transcripts, or unbounded lists

{
  "ok": true,
  "command": "mycli logs",
  "result": {
    "lines": 20,
    "total": 4582,
    "truncated": true,
    "full_output": "/var/folders/.../mycli-logs-abc123.log",
    "entries": ["...last 20 lines..."]
  },
  "next_actions": [
    {
      "command": "mycli logs <source> [--lines <lines>]",
      "description": "Show more log lines",
      "params": {
        "source": { "enum": ["worker", "errors", "server"], "default": "worker" },
        "lines": { "default": 20, "description": "Number of lines" }
      }
    }
  ]
}

5. Errors suggest fixes

When something fails, the response includes a fix field — plain language telling the agent what to do about it.

{
  "ok": false,
  "command": "mycli send pipeline/video.download",
  "error": {
    "message": "Server not responding",
    "code": "SERVER_UNREACHABLE"
  },
  "fix": "Start the server: docker compose up -d",
  "next_actions": [
    { "command": "mycli status", "description": "Re-check system health after fix" }
  ]
}

Response Envelope

Every command uses this exact shape:

Success

{
  ok: true,
  command: string,          // the command that was run
  result: object,           // command-specific payload
  next_actions: Array<{
    command: string,        // command template (POSIX syntax) or literal
    description: string,    // what it does
    params?: Record<string, {   // presence = command is a template
      description?: string,     // what this param means
      value?: string | number,  // pre-filled from current context
      default?: string | number,// value if omitted
      enum?: string[],          // valid choices
      required?: boolean        // true for <positional> args
    }>
  }>
}

Error

{
  ok: false,
  command: string,
  error: {
    message: string,        // what went wrong
    code: string            // machine-readable error code
  },
  fix: string,              // plain-language suggested fix
  next_actions: Array<{
    command: string,        // command template or literal
    description: string,
    params?: Record<string, { ... }>  // same schema as success
  }>
}

Implementation

Framework: Effect CLI (@effect/cli)

All CLIs use @effect/cli with Bun. This is non-negotiable — consistency across the system matters more than framework preference.

import { Command, Options } from "@effect/cli"
import { BunContext, BunRuntime } from "@effect/platform-bun"

const send = Command.make("send", {
  event: Options.text("event"),
  data: Options.optional(Options.text("data").pipe(Options.withAlias("d"))),
}, ({ event, data }) => {
  // ... execute, return JSON envelope
})

const root = Command.make("mycli", {}, () => {
  // Root: return health + command tree
}).pipe(Command.withSubcommands([send, status, logs]))

Binary distribution

Build with Bun, install to ~/.bun/bin/:

bun build src/cli.ts --compile --outfile mycli
cp mycli ~/.bun/bin/

Adding a new command

Define the command with Command.make
Return the standard JSON envelope (ok, command, result, next_actions)
Include contextual next_actions — what makes sense AFTER this specific command
Handle errors with the error envelope (ok: false, error, fix, next_actions)
Add to the root command's subcommands
Add to the root command's commands array in the self-documenting output
Rebuild and install

Streaming Protocol (NDJSON)

Request-response covers the spatial dimension (what's the state now?). Streamed NDJSON covers the temporal dimension (what's happening over time?). Together they make the full system observable through one protocol.

When to stream

Stream when the command involves temporal operations — watching, following, tailing. Not every command needs streaming. Point-in-time queries (status, list) stay as single envelopes.

Streaming is activated by command semantics (--follow, watch), never by a global --stream flag.

Protocol: typed NDJSON with HATEOAS terminal

Each line is a self-contained JSON object with a type discriminator. The last line is always the standard HATEOAS envelope (result or error). Tools that don't understand streaming read the last line and get exactly what they expect.

{"type":"start","command":"mycli run --follow","ts":"2026-02-19T08:25:00Z"}
{"type":"step","name":"download","status":"started","ts":"..."}
{"type":"progress","name":"download","percent":45,"ts":"..."}
{"type":"step","name":"download","status":"completed","duration_ms":3200,"ts":"..."}
{"type":"step","name":"transcribe","status":"started","ts":"..."}
{"type":"log","level":"warn","message":"Large file, chunked processing","ts":"..."}
{"type":"step","name":"transcribe","status":"completed","duration_ms":45000,"ts":"..."}
{"type":"result","ok":true,"command":"...","result":{...},"next_actions":[...]}

Stream event types

| Type | Meaning | Terminal? | |------|---------|-----------| | start | Stream begun, echoes command | No | | step | Step lifecycle (started/completed/failed) | No | | progress | Progress update (percent, bytes, message) | No | | log | Diagnostic message (info/warn/error level) | No | | event | An event was emitted (fan-out visibility) | No | | result | HATEOAS success envelope — always last | Yes | | error | HATEOAS error envelope — always last | Yes |

TypeScript types

import type { NextAction } from "./response"

type StreamEvent =
  | { type: "start"; command: string; ts: string }
  | { type: "step"; name: string; status: "started" | "completed" | "failed"; duration_ms?: number; error?: string; ts: string }
  | { type: "progress"; name: string; percent?: number; message?: string; ts: string }
  | { type: "log"; level: "info" | "warn" | "error"; message: string; ts: string }
  | { type: "event"; name: string; data: unknown; ts: string }
  | { type: "result"; ok: true; command: string; result: unknown; next_actions: NextAction[] }
  | { type: "error"; ok: false; command: string; error: { message: string; code: string }; fix: string; next_actions: NextAction[] }

Composable with Unix tools

NDJSON is pipe-native. Agents and humans can filter streams:

# Only step events
mycli watch | jq --unbuffered 'select(.type == "step")'

# Only failures
mycli run --follow | jq --unbuffered 'select(.type == "error" or (.type == "step" and .status == "failed"))'

Agent consumption pattern

Agents consuming streams read lines as they arrive and can make decisions mid-execution:

Start the stream
Read lines incrementally
React to early signals (cancel if error, escalate if slow, log progress)
The terminal result/error line contains next_actions for what to do after

This eliminates the polling tax — no wasted tool calls checking "is it done yet?"

Anti-Patterns

| Don't | Do | |-------|-----| | Plain text output | JSON envelope | | Tables with ANSI colors | JSON arrays | | --json flag to opt into JSON | JSON is the only format | | Dump 10,000 lines | Truncate + file pointer | | Error: something went wrong | { ok: false, error: {...}, fix: "..." } | | Undiscoverable commands | Root returns full command tree | | Static help text | HATEOAS next_actions | | console.log("Success!") | { ok: true, result: {...} } | | Exit code as the only error signal | Error in JSON + exit code | | Require the agent to read --help | Root command self-documents | | Subcommand with no withDescription | Every command gets a description for --help | | Poll in a loop for temporal data | Stream NDJSON | | Plain text in streaming commands | Every line is a typed JSON object |

Naming Conventions

Commands are nouns or verbs, lowercase, no hyphens: send, status, logs
Subcommands follow naturally: mycli search "query", mycli run start
Flags use --kebab-case: --max-quality, --follow
Short flags for common options: -d for --data, -f for --follow

Checklist for New Commands

[ ] Returns JSON envelope (ok, command, result, next_actions)
[ ] Command.withDescription() set (shows in --help)
[ ] Error responses include fix field
[ ] Root command lists this command in its tree
[ ] Output is context-safe (truncated if potentially large)
[ ] next_actions are contextual to what just happened
[ ] next_actions with variable parts use template syntax (<required>, [--flag <value>]) + params
[ ] Context-specific values pre-filled via params.*.value
[ ] No plain text output anywhere
[ ] No ANSI colors or formatting
[ ] Works when piped (no TTY detection)
[ ] Builds and installs

Agent Skills: This is the ONLY output format

Install this agent skill to your local

Skill Files