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.
npx skills add promptdriven/pdd --skill pdd-promptinggit clone --depth 1 https://github.com/promptdriven/pddWrote 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.
[](https://agentmods.dev/skills/promptdriven/pdd/pdd-prompting)<a href="https://agentmods.dev/skills/promptdriven/pdd/pdd-prompting"><img src="https://agentmods.dev/badge/skills/promptdriven/pdd/pdd-prompting/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.
<a href="https://agentmods.dev/skills/promptdriven/pdd/pdd-prompting"><img src="https://agentmods.dev/badge/skills/promptdriven/pdd/pdd-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00060 | $0.00600 |
| Opus 5.5 | $0.00024 | $0.00240 |
| Sonnet 5.5 | $0.00012 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
pdd-prompting 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDD prompting
In PDD, prompts are the source. Each code module has one .prompt.md file; the code implements it.
Core rules
- Read
guide.mdin full before you write or change a prompt, Story or test cases. A link or a summary is not enough. Read RUNBOOK.md §2–§4 before you write a prompt or a test file. - Change the prompt first, then the code.
- Write one prompt for each module: what it must do and why, not the code line by line.
- Give each rule one owner prompt. Link to a shared rule. Do not copy it. For a CLI, say if a rule belongs to the whole-CLI prompt or to one module's prompt.
- Keep the behavior callers need and the edge cases that matter.
- Write expected results from the requirement before the code exists. Never copy them from the code's output.
- Show the prompt, Story and cases to the person before you build. The person decides; never approve for them.
- Report only checks that you ran, with their real output.
Files
guide.md: the full Prompting guide.review.md: how to review drafts and report results.RUNBOOK.md: how to write prompts and tests that the runtime can check (§2–§10), and how to runpdd checkandpdd try.
How to write
- Tell the person which rules of
guide.mdapply. - Find the prompt that owns the behavior. Use the repo's paths.
- Write or change the prompt. Then write the Story in the person's words, with no function calls or type names. A Story is one behavior that a person can check in about a minute: one "I can…" sentence.
- Write test cases for normal input, limits and errors, with expected results from the prompt and the Story.
- Show the drafts and mark open questions. Ask only about choices that change the result.
- After you write or change a prompt, its Story and its test file, run
pdd checkas RUNBOOK.md says, and show the person theRuntime checkline(s) and the report link(s). Then offerpdd try STORYso they can use it by hand. If a check fails, show it; never change the expected value yourself.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 39 lines · 60 tokens per session scan A 5a974559504f
pdd-prompting is a skill published in the GitHub repository promptdriven/pdd (920 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 600 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.
Other skills, from other repositories
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
implement
Use when an approved plan and task list exist and it is time to turn them into working, tested code — the SDD phase after analyze and before verify. Enforces TDD: a failing test comes before the code that makes it pass, one task at a time, appended to a progress ledger that survives compaction. Delegates test tooling…
code-runner
A sandboxed code execution tool that runs short programs without using your computer's files or network. It supports Python, JavaScript, TypeScript, Go, Rust, Java, C, C++, Ruby, and PHP.
agent-browser
Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.
knowledge-engineering-quality-and-delivery-performance-security-and-snapshot-gates
A set of quality gates that checks performance, security, dependencies, test coverage, and stable output snapshots.
knowledge-engineering-quality-and-delivery-real-api-qualification-and-e2e
A guide to tests that call real AI providers and verify complete user flows across the CLI, web interface, terminals, and ACP hosts.