workspace-dispatch

A single-agent workflow manager that breaks a larger goal into smaller tasks, gives each task to a worker, and checks the result before continuing.

In plain words
What is it for?
Use it for multi-step coding, research, or code-review missions where each step can be checked with commands such as compiling code or confirming that a file exists.
Why use it?
It removes the need to manually coordinate dependent tasks or decide whether each step is finished. Failed checks can cause a task to be retried.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/outsourc-e/clawsuite/workspace-dispatch
Any agent
npx skills add outsourc-e/clawsuite --skill workspace-dispatch
Clone the repo
git clone --depth 1 https://github.com/outsourc-e/clawsuite

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 798 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00059 $0.00798
Opus 5 $0.00030 $0.00399
Sonnet 5 $0.00012 $0.00160
Haiku 4.5 $0.00006 $0.00080

Measured 3d ago against content hash baafbd95c225, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workspace-dispatch 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.

Origin

This is a copy

100% identical to workspace-dispatch — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/workspace-dispatch/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace Dispatch (Single Agent)

You are an autonomous mission orchestrator. Decompose work into tasks, spawn one worker per task, verify output, chain to the next — no user intervention needed.

Flow

  1. Decompose the goal into 2-6 tasks with machine-checkable exit criteria
  2. For each task: spawn a worker → wait → verify exit criteria → approve or retry
  3. Report summary when all tasks complete

Decomposition Rules

  • Max 6 tasks — keep it focused
  • Every task needs exit criteria verifiable with shell commands:
    • test -f /path — file exists
    • npx tsc --noEmit — compiles
    • grep -q "keyword" /path — contains expected content
    • wc -c < /path | awk '$1 > 100' — file has real content
  • No vague criteria — must be machine-checkable
  • Include working directory (cwd) for each task
  • Each task is independent — worker gets full context, no shared state between workers

Task Types

Type Worker Does Verify With
coding Write code, create files file exists, tsc passes
research Search, read, synthesize output file exists with content
review Read code, check behavior reviewer outputs PASS verdict

Dispatch Loop

For each task (in dependency order):
  1. Spawn worker:
     sessions_spawn(
       task: <worker prompt>,
       label: "worker-<task-slug>",
       mode: "run",
       runTimeoutSeconds: 600
     )
  2. sessions_yield() — wait for worker
  3. Verify exit criteria via exec commands
  4. If ALL pass → mark complete, next task
  5. If ANY fail → retry (max 3) with error context, then fail + skip dependents

Worker Prompt

Give each worker everything it needs in one prompt:

## Mission: {goal}
## Your Task: {task.title}
{task.description}

Working directory: {cwd}

## Exit Criteria (you MUST satisfy ALL):
- {criterion_1}
- {criterion_2}

## Rules
- Do NOT start servers or long-running processes
- Do NOT modify files outside your working directory
- Verify your own work before finishing — run the exit criteria commands yourself
- Commit when done

Read the full file on GitHub · 113 lines

Changes

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.

  1. 3d ago First seen · 113 lines · 59 tokens per session scan A baafbd95c225

Subscribe to this mod's changes

workspace-dispatch is a skill published in the GitHub repository outsourc-e/clawsuite (341 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 798 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to workspace-dispatch, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

asc-ppp-pricing

Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.

web-casa/DeepSeek-Harness-Desktop · 45 tokens

app-release

Use when the user asks to release a new version, ship a build, or publish a Skill Zoo release. Also use when a tag push results in Homebrew 404 errors or missing artifact failures.

luochang212/skill-zoo · 43 tokens

tauri-updater

Use when adding software auto-update to a Tauri 2 desktop app, or when users ask about tauri-plugin-updater integration, app update checking, distinguishing installer vs portable builds for updates, or generating update manifests for GitHub Releases.

luochang212/skill-zoo · 53 tokens

worth-fix

分析和判断任何论断、报告、想法或需求的真实性、价值与做法。当用户说"这个 bug 是真的吗"、"分析一下这个问题/这个报告/这个说法"、"这个修复值得做吗"、"帮我看下这个建议靠不靠谱",或用户给出一个待评估的 bug 报告、文章摘录、设计提案时使用。先核验、复现、定级、讲清原理、判断是否值得做,而不是直接相信或直接动手改代码。也适用于评估"要不要重构"。.

luochang212/skill-zoo · 134 tokens

skill_creator

创建、导入和适配天工 Skill 的交互式工作流。支持从零创建新 Skill,也支持从 GitHub 等外部来源导入并适配为天工格式。.

silent-rs/silent-Tiangong · 0 tokens

npm-release

Use when publishing or preparing to publish an npm package from this repository, especially the Skill Zoo CLI package under packages/cli. Also use when npm publish fails because of duplicate versions, npm authentication, browser authentication, dist-tag propagation, tarball contents, bin entry issues, or…

luochang212/skill-zoo · 66 tokens