A planning guide for uncertain product work, from defining the problem to checking results after release. It records what is proven, what is still a guess, and what to test next.

Use it to define measurable goals, turn design choices into testable claims, build small prototypes, record decisions, and decide whether work is ready to implement or needs more testing.

It prevents teams from treating untested ideas as facts and helps them gather useful evidence before spending heavily on a product, experiment, feature, or risky code change.

ai-pdlc — Skill for Codex by ashermahonin/agentic-skills

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 ashermahonin/agentic-skills --skill ai-pdlc

Clone the repo

git clone --depth 1 https://github.com/ashermahonin/agentic-skills

Made for: 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/ashermahonin/agentic-skills/ai-pdlc/github.svg)](https://agentmods.dev/skills/ashermahonin/agentic-skills/ai-pdlc)

Your own site

<a href="https://agentmods.dev/skills/ashermahonin/agentic-skills/ai-pdlc"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/ai-pdlc/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/ashermahonin/agentic-skills/ai-pdlc"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/ai-pdlc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 857 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	$0.00066	$0.00857
Opus 5.5	$0.00026	$0.00343
Sonnet 5.5	$0.00013	$0.00171
Haiku 4.5	$0.00007	$0.00086

Measured 2mo ago against content hash 1a180ad5d219, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-pdlc 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 2mo 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.

agentic/skills/ai-pdlc/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI PDLC

Purpose

Organize uncertain product work around evidence. sdlc-orchestrator chooses the operational route; this skill records what each product phase has established, what remains a hypothesis, and what should be tested next.

Inputs

Read references/pdlc-phases.md.
Pull the product intent and constraints from intake-coordinator.
Pull existing research from research-domain and competitive-analysis (if present); request them if missing.
Restate the project as 3–5 falsifiable hypotheses, each with a "kill" criterion and a cheapest-useful-evidence step.
Use Context7 MCP to validate any external technology, market, or platform-policy claim that gates a hypothesis.

Decision process

Phase 0 — Define. Lock product intent, success metric, primary user, and platform matrix (with platform-detector).
Phase 1 — Discover. Run research-domain + competitive-analysis. Record what is known and what is still guess.
Phase 2 — Hypothesize. Use hypothesis-validator to express each top design choice as a falsifiable claim with a measurable kill criterion.
Phase 3 — Prototype. Build the smallest artifact that disproves or supports the riskiest hypothesis. Throwaway is allowed.
Phase 4 — Plan. With requirements-quality, architecture-review, user-journey-mapper, and decompose-work, turn surviving hypotheses into requirements, ADRs, journeys, epics, stories.
Phase 5 — Implement. Run each story through tdd-workflow then service-implementation. No production code before the failing test and implementation contract exist.
Phase 6 — Harden. Route the build through the matching security skill (security-owasp-web, security-mobile-masvs, security-owasp-llm, or security-owasp-agentic) plus cve-zero-day-scanner before release.
Phase 7 — Ship. Use qa-eval for release readiness and documentation-graph-curator to sync project memory and the Obsidian graph.
Phase 8 — Evaluate. Compare measured outcome against the original hypothesis kill criterion. Record what was proven, what was wrong, and what to learn next.

Read the full file on GitHub · 61 lines

Files

What ships with it

2 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.

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.

2mo ago First seen · 61 lines · 66 tokens per session scan A 1a180ad5d219

Subscribe to this mod's changes

ai-pdlc is a skill published in the GitHub repository ashermahonin/agentic-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 857 once invoked, about $0.0003 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 2026-08-31.

Planning

ai-pdlc next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-pdlcashermahonin/agentic-skills	Skill	10	2mo ago	MIT	A	66	Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code