Orchestrate

What it does

When your agent uses it

• : declaring an intent (audit/research/feature shape) and wanting a planner agent to derive the skill workflow
• Run read-only fanout with fail-closed no-change verification

Example prompts

• “/orchestrate”

Requirements

• Node.js
• Pre-approved tools (allowed-tools): Bash(node:*), Bash(git status:*), Bash(git diff:*), Bash(git log:*), Bash(git rev-parse:*), Bash(git check-ignore:*), Read, Grep, Glob, Agent, Task, Write, AskUserQuestion

What it can do on your machine

Read from SKILL.md and the folder at commit c9a2036. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash(node:*)
  • Bash(git status:*)
  • Bash(git diff:*)
  • Bash(git log:*)
  • Bash(git rev-parse:*)
  • Bash(git check-ignore:*)
  • Read
  • Grep
  • Glob
  • Agent

  …and 3 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 4 files in scripts/ (JavaScript), which the agent can run.

  Shell commands in SKILL.md call:

  • node

  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 no API keys, tokens, secrets or passwords.

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

Context cost

Orchestrate loads about 2.5k tokens when it runs, and up to ~6.7k if it reads all its reference files. Until then it costs about 120 tokens; SKILL.md has 699 words of instructions outside code blocks.

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

~120

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

~2.5k

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

~6.7k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from sd0xdev/sd0x-harness at commit c9a2036, republished under its MIT licence (© sd0xdev). 699 words, ~2,495 tokens.

name

orchestrate

description

Agent-driven workflow orchestration (v1 report-only). Use when: declaring an intent (audit/research/feature shape) and wanting a planner agent to derive the skill workflow, preview it, and run read-only fanout with fail-closed no-change verification. Not for: executing mutating steps (v1 emits them as proposed-manual), code review (use codex-review-fast), doc review (use codex-review-doc). Output: plan preview + run summary + report via existing doc-review loop.

allowed-tools

Bash(node:*), Bash(git status:*), Bash(git diff:*), Bash(git log:*), Bash(git rev-parse:*), Bash(git check-ignore:*), Read, Grep, Glob, Agent, Task, Write, AskUserQuestion

sequenceDiagram
    participant U as User
    participant C as Claude（主 session）
    participant S as scripts
    participant P as Planner（Explore，admission 約束）
    participant W as Fanout workers（read-only）
    U->>C: /orchestrate "意圖" --execute
    C->>S: plan-context.js --out（封包寫檔，主 session 只收摘要）
    C->>S: run-verify.js snapshot > .claude_workflows/<run-id>/baseline.json（digest 由 stderr 收進 session）
    C->>P: 背景派發 planner（傳封包路徑，非內容）
    P->>P: Read 封包
    P-->>C: plan JSON
    C->>S: run-verify.js compare --baseline-sha256（planning 後立即驗）
    C->>S: validate-plan.js --context-sha256 <摘要 sha256>（admission + gate lint + 封包完整性）
    C->>U: Plan preview + AskUserQuestion
    U-->>C: 核可
    C->>C: Write run-state（redact 先行）
    loop 每個 parallel_group（≤ max_waves）
        C->>W: 平行派發（單訊息）
        W-->>C: findings（context packet）
    end
    C->>S: run-verify.js compare --baseline-sha256（同一 baseline，同一 digest）
    alt drift
        C->>U: ⚠️ Need Human（run 標 failed，不寫報告）
    else 無變更
        C->>C: Write 報告 → /codex-review-doc 接手
    end

Input: /orchestrate "audit 全 repo hook 的 fail-open 路徑" --execute
Action: context → snapshot → planner → lint → preview → 核可 → 3× Explore fanout → compare → 報告 → doc review

Input: /orchestrate "完成 feature X 並確保品質"
Action: 規劃 + 預覽即止——mutating 步驟以 proposed-manual 列出（含 code-review + precommit gate），交人走正常流程

© sd0xdev, 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 8 other files (scripts, references) in skills/orchestrate of sd0xdev/sd0x-harness.

• SKILL.md
• references/admission-allowlist.json
• references/execution-policy.md
• references/plan-schema.md
• references/planner-prompt.md
• scripts/plan-context.js
• scripts/prune-runs.js
• scripts/run-verify.js
• scripts/validate-plan.js

Open the folder on GitHubat commit c9a2036