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.
/plugin marketplace add kimsanguine/hplannpx agentmods add plugins/kimsanguine/hplan/delivergit clone --depth 1 https://github.com/kimsanguine/hplanGrade 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 2d 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.
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/"
}
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.
- 2d ago First seen · 42 lines scan A 30e376b43405
deliver is a plugin published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 16d 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.
Other plugins, from other repositories
linear
Linear issue tracking integration. Create issues, manage projects, update statuses, search across workspaces, and streamline your software development workflow with Linear's modern issue tracker.
produck-skills
Pull real in-context user feedback into your coding agent and ship aligned fixes. Bundles the produck MCP (searchfeedback, getfeedback), a feedback-to-fix guide skill, and the user-alignment PRD skill.
produck
Plugin marketplace listing 1 plugin: produck.
goal-workflow
An AI-driven development workflow — from PRD to shipped code, all within Claude Code.
personal-corp-os
Personal Corp OS: run a one-person company through AI agents with a weekly rhythm, department repos, safe public releases, and open Claude Code and Codex skills.
personal-corp-os
Personal Corp framework: run your business with AI agents through GitHub, department repos, safe public releases, Telegram, agent gateways, html-draft diagrams, and media/art-direction workflows.