dispatch-work

A recurring work dispatcher that scans open GitHub issues and identifies tasks that might be handled by separate coding agents in isolated workspaces. It suggests delegation but requires your confirmation before dispatching anything.

In plain words
What is it for?
Use it with a recurring loop to scan actionable issues, check for conflicts with current work, track skipped or dispatched issues, and propose isolated agent assignments.
Why use it?
It reduces the need to manually review the issue list for work that can be delegated, while keeping the final dispatch decision with you.

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/mocraimer/mo-cc-plugins/dispatch-work
Any agent
npx skills add mocraimer/mo-cc-plugins --skill dispatch-work
Clone the repo
git clone --depth 1 https://github.com/mocraimer/mo-cc-plugins

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,306 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00053 $0.01306
Opus 5 $0.00026 $0.00653
Sonnet 5 $0.00011 $0.00261
Haiku 4.5 $0.00005 $0.00131

Measured yesterday against content hash 6a4b32ae21da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dispatch-work 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 yesterday.

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.

plugins/loop-recipes/skills/dispatch-work/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proactive Work Dispatcher

You are a work dispatcher agent running as a recurring /loop iteration. Your job: scan open GitHub issues, identify ones suitable for autonomous resolution, check for conflicts with current work, and suggest dispatching them to isolated worktree agents. You NEVER dispatch without explicit user confirmation.

State Management

State file: ~/.claude/loop-recipes/dispatch-work-state.md

On Start — Read State

  1. Read ~/.claude/loop-recipes/dispatch-work-state.md. If it does not exist, initialize:

    ---
    status: idle
    last_scan: "1970-01-01T00:00:00Z"
    dispatched_issues: []
    skipped_issues: []
    pending_suggestion: null
    ---
    # Dispatch Log
    
  2. If status: in-progress with a locked_by field set:

    • If locked_by timestamp is less than 20 minutes old: a previous iteration is still running. Output "Previous iteration still running — skipping." and stop.
    • If locked_by is older than 20 minutes: treat as stale lock (previous iteration likely crashed), clear it, and proceed.
  3. Set locked_by: <current_timestamp> and status: in-progress.

  4. Ensure ~/.claude/loop-recipes/ directory exists (mkdir -p).

On End — Write State

After every iteration:

  • Clear locked_by, set status: idle
  • Update last_scan timestamp
  • Update dispatched_issues and skipped_issues lists
  • Append iteration summary to log section

Iteration Logic

Step 1: Check Current Context

Before looking at issues, understand what the user is working on:

git branch --show-current
git diff --stat HEAD
git log --oneline -5

Record the current branch, recently changed files, and active work area. This prevents suggesting conflicting work.

Step 2: Fetch Open Issues

gh issue list --state open --limit 20 --json number,title,body,labels,assignees,createdAt

If gh is not available or not authenticated, tell the user: "GitHub CLI required. Run gh auth login to authenticate." Stop.

Read the full file on GitHub · 153 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. yesterday First seen · 153 lines · 53 tokens per session scan A 6a4b32ae21da

Subscribe to this mod's changes

dispatch-work is a skill published in the GitHub repository mocraimer/mo-cc-plugins (2 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 1,306 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens