Opcode

What it does

When your agent uses it

• Defining workflows
• Running templates
• Checking status
• Sending signals

Example prompts

• “/opcode”

Requirements

• A credential in OPCODE_VAULT_KEY
• Compatibility (from SKILL.md): Requires Go 1.25+, CGO_ENABLED=1, and gcc or clang. Runs as SSE daemon on macOS and Linux. Linux: cgroups v2 for process isolation. macOS: timeout-only fallback.

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Workflow reaches a reasoning step
2. 2Executor creates PendingDecision, emits decision_requested event
3. 3Workflow status becomes suspended
4. 4Agent calls opcode.status to see pending decision with context and options
5. 5Agent resolves via opcode.signal
6. 6Workflow auto-resumes after signal
7. 7If timeout expires: fallback option auto-selected, or step fails if no fallback

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • go

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • OPCODE_VAULT_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires Go 1.25+, CGO_ENABLED=1, and gcc or clang. Runs as SSE daemon on macOS and Linux. Linux: cgroups v2 for process isolation. macOS: timeout-only fallback.

  From compatibility in the SKILL.md frontmatter.

Context cost

Opcode loads about 4.8k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 123 tokens; SKILL.md has 1,148 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~123

When it runs · the whole SKILL.md, loaded when a task matches

~4.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~18k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,148 words, ~4,803 tokens.

name

opcode

description

Zero-token execution layer for AI agents. Define workflows once, run them free forever — persistent, scheduled, deterministic. 6 MCP tools over SSE. Supports DAG-based execution, 6 step types (action, condition, loop, parallel, wait, reasoning), 26 built-in actions, ${{}} interpolation, reasoning nodes for human-in-the-loop decisions, and secret vault. Use when defining workflows, running templates, checking status, sending signals, querying workflow history, or visualizing DAGs.

compatibility

Requires Go 1.25+, CGO_ENABLED=1, and gcc or clang. Runs as SSE daemon on macOS and Linux. Linux: cgroups v2 for process isolation. macOS: timeout-only fallback.

license

MIT

metadata.version

1.2.1

metadata.transport

sse

metadata.author

rendis

metadata.repository

https://github.com/rendis/opcode

metadata.primary-env

OPCODE_VAULT_KEY

metadata.platforms

darwin linux

metadata.requires-bins

go gcc|clang

metadata.openclaw-emoji

⚙️

metadata.openclaw-os

darwin linux

go install github.com/rendis/opcode/cmd/opcode@latest

opcode install --listen-addr :4100 --vault-key "my-passphrase"

{
  "mcpServers": {
  "mcpServers": {
    "opcode": {
      "type": "sse",
      "url": "http://localhost:4100/sse"
    }
  }
}

{
  "workflow_id": "uuid",
  "status": "completed | suspended | failed",
  "output": { ... },
  "started_at": "RFC3339",
  "completed_at": "RFC3339",
  "steps": {
    "step-id": { "step_id": "...", "status": "completed", "output": {...}, "duration_ms": 42 }
  }
}

{
  "workflow_id": "uuid",
  "status": "suspended",
  "steps": { "step-id": { "status": "...", "output": {...} } },
  "pending_decisions": [
    {
      "id": "uuid",
      "step_id": "reason-step",
      "context": { "prompt": "...", "data": {...} },
      "options": [ { "id": "approve", "description": "Proceed" } ],
      "timeout_at": "RFC3339",
      "fallback": "reject",
      "status": "pending"
    }
  ],
  "events": [ ... ]
}

{
  "steps": [ ... ],
  "inputs": { "key": "value or ${{secrets.KEY}}" },
  "context": { "intent": "...", "notes": "..." },
  "timeout": "5m",
  "on_timeout": "fail | suspend | cancel",
  "on_complete": { /* step definition */ },
  "on_error": { /* step definition */ },
  "metadata": {}
}

{
  "id": "step-id",
  "type": "action | condition | loop | parallel | wait | reasoning",
  "action": "http.get",
  "params": { ... },
  "depends_on": ["other-step"],
  "condition": "CEL guard expression",
  "timeout": "30s",
  "retry": { "max": 3, "backoff": "exponential", "delay": "1s", "max_delay": "30s" },
  "on_error": { "strategy": "ignore | fail_workflow | fallback_step | retry", "fallback_step": "id" },
  "config": { /* type-specific */ }
}

{
  "id": "route",
  "type": "condition",
  "config": {
    "expression": "inputs.env",
    "branches": { "prod": [...], "staging": [...] },
    "default": [...]
  }
}

{
  "id": "process-items",
  "type": "loop",
  "config": {
    "mode": "for_each",
    "over": "[\"a\",\"b\",\"c\"]",
    "body": [
      {
        "id": "hash",
        "action": "crypto.hash",
        "params": { "data": "${{loop.item}}" }
      }
    ],
    "max_iter": 100
  }
}

{
  "id": "fan-out",
  "type": "parallel",
  "config": {
    "mode": "all",
    "branches": [
      [{ "id": "a", "action": "http.get", "params": {...} }],
      [{ "id": "b", "action": "http.get", "params": {...} }]
    ]
  }
}

{ "id": "pause", "type": "wait", "config": { "duration": "5s" } }

{
  "id": "review",
  "type": "reasoning",
  "config": {
    "prompt_context": "Review data and decide",
    "options": [
      { "id": "approve", "description": "Proceed" },
      { "id": "reject", "description": "Stop" }
    ],
    "data_inject": { "analysis": "steps.analyze.output" },
    "timeout": "1h",
    "fallback": "reject",
    "target_agent": ""
  }
}

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in skills/opcode of LeoYeAI/openclaw-master-skills.

• SKILL.md
• _meta.json
• references/actions.md
• references/error-handling.md
• references/expressions.md
• references/operations.md
• references/patterns.md
• references/workflow-schema.md

Open the folder on GitHubat commit e5199b5