prp-deliver

prp-deliver is a skill for Claude Code from Wirasm/prp. It costs 28 tokens per session (1,428 once invoked), scanned A, original, MIT.

An experimental workflow for taking a software task from its source material through implementation, review, corrections, and a pull request ready for merging.

In plain words
What is it for?
Use it when you need to coordinate specialists to plan a change, implement it, review it, fix review findings, and publish the result with passing CI.
Why use it?
It keeps planning, coding, independent review, and CI checks connected so unfinished or weakly reviewed changes are less likely to be delivered.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: positional $N argument; installed under .agents/ (shared by several agents); $skill-name invocation.

About the project

PRP is a collection of prompts and workflows for AI-assisted software development with Claude Code. Its Product Requirement Prompts combine product requirements, selected codebase context, and an execution runbook so a coding agent can implement a vertical slice of software. The catalogue entries are the project’s own skills, agents, instructions, hook, and plugin workflows.

Wirasm/prp · 2,242 stars · on GitHub

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/wirasm/prp/prp-deliver
Any agent
npx skills add Wirasm/prp --skill prp-deliver
Clone the repo
git clone --depth 1 https://github.com/Wirasm/prp

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.

agentmods badge for prp-deliver

README.md
[![agentmods](https://agentmods.dev/badge/skills/wirasm/prp/prp-deliver.svg)](https://agentmods.dev/skills/wirasm/prp/prp-deliver)
Your own site
<a href="https://agentmods.dev/skills/wirasm/prp/prp-deliver"><img src="https://agentmods.dev/badge/skills/wirasm/prp/prp-deliver.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,428 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 5.1 $0.00028 $0.01428
Opus 5 $0.00014 $0.00714
Sonnet 5 $0.00006 $0.00286
Haiku 4.5 $0.00003 $0.00143

Measured 6d ago against content hash a84bdf926c84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

prp-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 6d 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.

.agents/skills/prp-deliver/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arguments: $ARGUMENTS (and $1, $2, ...) refer to the arguments given when this skill was invoked. Take them from the user's request; if absent, infer them from the conversation.

Deliver to a Reviewed PR

Own one outcome from source input to a published READY TO MERGE review and green CI. Act as the sub-orchestrator for this delivery: start and steer specialist agents, preserve their handoff artifacts, and do not implement or review the work in this context.

Input: $ARGUMENTS (if absent, use the conversation).

Ownership contract

  • Continue autonomously through plan, implementation, PR, review, correction, re-review, and CI. A published report is observable progress, not a pause point.
  • Run stages sequentially in the delivery owner's checkout. Only one implementation or correction agent may mutate it at a time.
  • Use a fresh agent for planning, a fresh agent for implementation, and a fresh independent agent for every review. Resume the implementation agent for corrections while it remains available.
  • Keep the plan path, implementation report, PR, latest review report, publication URL, and agent handles. Durable artifacts—not recalled summaries—cross context windows.
  • Keep a verbatim caller-decisions record of two kinds: constraints that bind the whole delivery, such as scope, base, and product decisions; and dispositions attached to one finding or blocker. A constraint applies to every later stage. A disposition applies only to the finding it names, while that finding is live. Update the record when the caller resolves a blocker, and pass each fresh agent the constraints plus the dispositions its stage acts on, verbatim.
  • Carry the burden of proof. Prove completion with green validation, the live PR, the complete published review, its READY TO MERGE verdict, and green required CI.
  • Stop only when a product decision, missing prerequisite primitive, inaccessible dependency, permission boundary, or repeated no-progress failure cannot be resolved autonomously. Report the exact decision or access needed and a recommendation.
  • Do not merge the PR. The caller owns the merge gate.

Read the full file on GitHub · 72 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. 6d ago First seen · 72 lines · 28 tokens per session scan A a84bdf926c84

Subscribe to this mod's changes

prp-deliver is a skill published in the GitHub repository Wirasm/prp (2,242 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 1,428 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 2026-08-30.

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-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

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