A setup guide for adding prompt-driven development instructions to a repository’s agent instructions. It places a standard block in CLAUDE.md or AGENTS.md, creating the file when needed.

Use it when introducing this development process to a project or checking whether the required instructions are already installed.

It gives coding agents a consistent way to learn that prompts, stories, and tests come before implementation. It also avoids overwriting unrelated repository instructions.

pdd-setup — Skill for Claude Code and Codex by promptdriven/pdd

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 promptdriven/pdd --skill pdd-setup

Clone the repo

git clone --depth 1 https://github.com/promptdriven/pdd

Made for: Claude Code, Codex.

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/skills/promptdriven/pdd/pdd-setup/github.svg)](https://agentmods.dev/skills/promptdriven/pdd/pdd-setup)

Your own site

<a href="https://agentmods.dev/skills/promptdriven/pdd/pdd-setup"><img src="https://agentmods.dev/badge/skills/promptdriven/pdd/pdd-setup/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/skills/promptdriven/pdd/pdd-setup"><img src="https://agentmods.dev/badge/skills/promptdriven/pdd/pdd-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 426 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.00426
Opus 5.5	$0.00023	$0.00170
Sonnet 5.5	$0.00011	$0.00085
Haiku 4.5	$0.00006	$0.00043

Measured today against content hash 3f9f4d29326a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pdd-setup 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 today.

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.

skills/pdd-setup/SKILL.md · 26 lines

What it actually says

PDD setup

Add one short PDD block to the file that this repo's agents read. This skill only writes the block: if you can read it, the PDD skills are already installed. The pdd setup command writes the same block and also installs the skills when they are missing.

Pick the file: CLAUDE.md if it exists, else AGENTS.md. If neither exists, create AGENTS.md. Use the repo root.
Write this block exactly. Leave out the RUNBOOK.md line if the pdd-prompting skill has no RUNBOOK.md.
If the file already has a  …  block, replace only that block. Otherwise add the block at the end, after one empty line. Keep all other text.
If the block is already the same, change nothing. If only one marker is there, stop and ask the person.

<!-- pdd:start -->
## PDD
This project uses PDD: prompts are the source. Write the prompt, Story and test cases first, then the code.
Skills: pdd-prompting (the Prompting guide), pdd-feature, pdd-bug, pdd-small-change. Call one with `$pdd-feature` in Codex or `/pdd-feature` in Claude Code, or just ask for it by name.
Full run with PRs: `pdd workflow run NAME ISSUE` (NAME: feature, bug or small-change).
Before you write prompts or tests, read RUNBOOK.md in the pdd-prompting skill.
<!-- pdd:end -->

Never paste the guide or a workflow into the file. Show the person the diff.

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.

today First seen · 26 lines · 57 tokens per session scan A 3f9f4d29326a

Subscribe to this mod's changes

pdd-setup is a skill published in the GitHub repository promptdriven/pdd (920 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 426 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-28.

Building agents ai cli code developer-tools development methodology

pdd-setup

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

PDD setup

What this file has done since we first saw it

Other skills, from other repositories

sparc-methodology

logic-lens

knowledge-extension-ecosystem-lsp-code-intelligence

code-runner

github-explorer

code-review