dispatch-contract

dispatch-contract is a skill for Claude Code from Jamie-BitFlight/claude_skills. It costs 17 tokens per session (424 once invoked), scanned A, original, MIT.

A set of rules for choosing which agent handles a delegated development task and ensuring later steps use the resulting work.

In plain words
What is it for?
It is used when dispatching development-harness operations or independent reviews to other agents.
Why use it?
It prevents tasks from being sent to agents that lack the needed tools and prevents unused outputs from being produced.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

Part of the dh plugin — 53 skills, 28 agents shipped together

Good fit It is used when dispatching development-harness operations or independent reviews to other agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jamie-bitflight/claude_skills/dispatch-contract
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.

Any agent
npx skills add Jamie-BitFlight/claude_skills --skill dispatch-contract
Clone the repo
git clone --depth 1 https://github.com/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Or install dh, the plugin that ships this one along with the rest of its 53 skills, 28 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dispatch-contract

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/dispatch-contract.svg)](https://agentmods.dev/skills/jamie-bitflight/claude_skills/dispatch-contract)
Your own site
<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/dispatch-contract"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/dispatch-contract.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 424 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00017 $0.00424
Opus 5 $0.00009 $0.00212
Sonnet 5 $0.00003 $0.00085
Haiku 4.5 $0.00002 $0.00042

Measured 3d ago against content hash 794deba2b671, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

dispatch-contract 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.

plugins/development-harness/skills/dispatch-contract/SKILL.md · 45 lines

What it actually says

Dispatch Contract

<dispatch_selection>

A dispatch that hands over no dh operation — an independent review, say — has no dh-roster requirement to reach: any specialist that fits runs it, dh roster or not. Where its finding goes is never decided here — subagent-contract's <result_destination> clause governs that for every dispatch, review-only included.

Once a dispatch hands over one, dispatch a dh: specialist that fits the task and whose declared tools reach every operation handed over; failing that, dh:task-worker — this plugin's general-purpose worker, arriving with dh's tools and hooks. A profile resolves to an agent, so outside capability reaches a task two ways through dh:task-worker: an outside agent as the profile it loads, or an outside skill through the task's own skills list.

</dispatch_selection>

<artifact_consumption>

Every artifact is consumed as an input by a later step. An artifact no step reads is a missing consumer, not a redundant artifact.

</artifact_consumption>

<dispatch_prompt_scope>

A dispatch prompt for an agent that can reach the backlog item's own content (see that agent's dh:subagent-contract <dispatch_input> rule) carries an item reference and whatever a peer teammate computed this run that no item_ref lookup can retrieve — never content pasted from the item's own sections.

Never write a speculative conclusion, a pre-formed verdict, or hedged language ("likely", "probably", "seems") into a dispatch prompt for an agent whose value is independent judgement. "this is very likely `defect` — confirm this classification yourself" is a violation: it hands the receiving agent a conclusion to ratify, not a problem to classify. Give the agent the item reference and let it reach its own verdict.

</dispatch_prompt_scope>

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 · 45 lines · 17 tokens per session scan A 794deba2b671

Subscribe to this mod's changes

dispatch-contract is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 424 once invoked, about $0.0001 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 2026-09-03.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 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