agentmods.dev

pdd CLAUDE.md

A set of repository instructions for working on the public PDD command-line tool with Claude Code, including commands, model choices, and code style.

In plain words
What is it for?
Running tests, coverage, lint checks, and PDD generation or repair commands; choosing models safely in automated or interactive environments.
Why use it?
It gives the coding agent the project’s expected commands and boundaries, including which models may need human login and should be avoided automatically.

Instructions file

854 7d ago A scan 390 tokens original MIT
View the source file 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.

agentmods
npx agentmods add instructions/promptdriven/pdd/claude-md
Clone the repo
git clone --depth 1 https://github.com/promptdriven/pdd
Per session 390 This file is loaded in full into every session.
When invoked 390 The same file — it is already loaded in full.
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 $0.00390 $0.00390
Opus 5 $0.00195 $0.00195
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured yesterday against content hash 5b858176bc82, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pdd CLAUDE.md 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 yesterday.

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.

CLAUDE.md · 27 lines

What it actually says

Claude Code Notes

This repository contains the public PDD CLI. Keep changes focused on the open-source package and avoid adding private deployment or credential-backed workflow details.

Commands

  • Install dependencies: pip install -e ".[dev]" or pip install -e .
  • Run all tests: pytest -vv tests/
  • Run one test file: pytest -vv tests/test_module_name.py
  • Test with coverage: make coverage
  • Generate module: make generate MODULE=module_name
  • Fix module: make fix MODULE=module_name
  • Crash fix: make crash MODULE=module_name
  • Regression tests: make regression
  • Lint check: make lint or pylint pdd/<module>.py

Model Selection

  • llm_model.csv has an interactive_only column. Rows marked True (e.g. github_copilot/*, chatgpt/*, lm_studio/*, ollama/*) require interactive human auth (device-flow OAuth or a ChatGPT subscription / codex login token) or a running local server and hang in non-interactive contexts (Cloud Run, CI, library import). _select_model_candidates skips them in the automatic candidate cascade by default; set PDD_ALLOW_INTERACTIVE=1 from a terminal to opt in. An explicitly configured PDD_MODEL_DEFAULT is always honored.

Code Style

  • Python 3.12+, four-space indentation, and PEP 8 conventions.
  • Use type hints for public functions.
  • Keep imports grouped as standard library, third-party, then local.
  • Functions should have docstrings when behavior or side effects are not obvious.
  • Add tests for user-visible behavior and shared helper changes.
  • Pydantic v2 is used for structured validation.
  • The CLI is implemented with Click.
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. yesterday First seen · 27 lines · 390 tokens per session scan A 5b858176bc82

Subscribe to this mod's changes

pdd CLAUDE.md is an instructions file published in the GitHub repository promptdriven/pdd (854 stars, last pushed 7d ago), licensed MIT. It adds 390 tokens to every session, about $0.0019 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.

Code reviewData and AITestingaiclicodedeveloper-toolsdevelopmentmethodology
Related

Other instructions, from other repositories

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

cs CLAUDE.md

Instructions for boyter/cs, covering claude.md, project overview, build & test commands, architecture and query pipeline (pkg/search/).

boyter/cs · 1,022 tokens

CheatSheetSeries CLAUDE.md

Claude Code instructions for OWASP/CheatSheetSeries, covering claude.md and for maintainers.

OWASP/CheatSheetSeries · 112 tokens

dev-challenge CLAUDE.md

Instructions for micheltlutz/dev-challenge, covering claude.md, the one rule to internalise, slash commands, subagents and skills.

micheltlutz/dev-challenge · 543 tokens

flow-like frontend.instructions.md

Instructions for Rheosoph/flow-like, covering project coding standards for typescript and react, typescript guidelines, react guidelines, ui framework and code quality.

Rheosoph/flow-like · 273 tokens

Praxis CLAUDE.md

Instructions for BackToCimaCoppi/Praxis, covering praxis 贡献规范（ai 与人共同遵守）, 1. skill 格式, 2. 文档格式, 3. 脱敏红线（开源仓硬约束，最高优先级） and 4. 新增 skill 自检清单（提 pr 前逐条打勾）.

BackToCimaCoppi/Praxis · 1,745 tokens