A collection of workflows for specifying, building, and shipping AI agents. It includes product requirements, agent instructions, prompt design, sprint planning, progress tracking, build coordination, and design-quality checks.

Use it to write an agent PRD, design prompts and instructions, plan development, track delivery, coordinate build work, and review interface or stakeholder requirements.

It brings the planning and delivery work for an AI agent into related workflows, from the first specification through implementation and review.

deliver — Plugin for Claude Code by kimsanguine/hplan

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.

Clone the repo

git clone --depth 1 https://github.com/kimsanguine/hplan

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/kimsanguine/hplan/deliver/github.svg)](https://agentmods.dev/plugins/kimsanguine/hplan/deliver)

Your own site

<a href="https://agentmods.dev/plugins/kimsanguine/hplan/deliver"><img src="https://agentmods.dev/badge/plugins/kimsanguine/hplan/deliver/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/kimsanguine/hplan/deliver"><img src="https://agentmods.dev/badge/plugins/kimsanguine/hplan/deliver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 10 skills, 1 command cost 1,144 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

deliver 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 1mo 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.

deliver/.claude-plugin/plugin.json · 42 lines

What it actually says

{
  "name": "deliver",
  "version": "1.1.0",
  "description": "Spec, build, and ship AI agents — PRD templates (prd --mode roadmap for roadmaps), instruction design, prompt engineering, sprint planning, context budget, stakeholder mapping, build-execution scaffolding (harness-design, parallel-team worktrees, build-loop), prompt-level progress tracking (velocity, estimate, blocker-detect, track --mode checkpoint), UI/UX design-system enforcement (DESIGN.md, RESPECT.md), and async stakeholder review via ask-team --mode review. Use when writing agent PRDs, building agents, communicating progress to stakeholders, or enforcing design quality during the build cycle.",
  "author": {
    "name": "AI PM Skills Contributors",
    "url": "https://github.com/kimsanguine"
  },
  "repository": "https://github.com/kimsanguine/hplan",
  "license": "MIT",
  "keywords": [
    "agent",
    "prd",
    "instruction",
    "prompt",
    "sprint",
    "pm",
    "stakeholder",
    "plan-review",
    "mermaid",
    "respect",
    "checkpoint",
    "harness",
    "worktree",
    "build-loop",
    "track",
    "progress",
    "gate",
    "design-system",
    "design-md",
    "respect-md",
    "mobile-check",
    "wcag",
    "ui-drift",
    "craft",
    "roadmap-mode",
    "ask-team-review"
  ],
  "skills": "./skills/",
  "commands": "./commands/"
}

Contents

What it installs

The manifest is a name and a version. 10 skills, 1 command travel with it, and installing the plugin installs all of them — 1,144 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

1mo ago First seen · 42 lines scan A 30e376b43405

Subscribe to this mod's changes

deliver is a plugin published in the GitHub repository kimsanguine/hplan (3 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Building agents Planning ai ai-agent ai-pm claude-code-plugin pm-tools skills

deliver

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

What it actually says

What it installs

What this file has done since we first saw it

Other plugins, from other repositories

sd0x-dev-flow

gan-zhong-xue

yield-xyz-agentkit-builder

skill-engine

ed3d-extending-claude

ed3d-00-getting-started