pdlc

pdlc is a skill for Claude Code from tomzx/agents. It costs 30 tokens per session (3,765 once invoked), scanned A, original, MIT.

A workflow that manages the full product development lifecycle, from discovering a problem through deciding what to build, launching it, and measuring the result.

In plain words
What is it for?
Use it to run multiple product phases in order, maintain their documents and decisions, return to an earlier phase when needed, and hand accepted requirements to software development.
Why use it?
It keeps product decisions connected across stages and requires a proceed, pivot, or kill decision at each major checkpoint instead of moving forward by default.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Good fit Use it to run multiple product phases in order, maintain their documents and decisions, return to an earlier phase when needed, and hand accepted requirements to software development.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/pdlc
View source ↗ tomzx/agents
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 tomzx/agents --skill pdlc
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

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 pdlc

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/pdlc/github.svg)](https://agentmods.dev/skills/tomzx/agents/pdlc)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/pdlc"><img src="https://agentmods.dev/badge/skills/tomzx/agents/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.

agentmods 80×15 button for pdlc

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/pdlc"><img src="https://agentmods.dev/badge/skills/tomzx/agents/pdlc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,765 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00030 $0.03765
Opus 5 $0.00015 $0.01883
Sonnet 5 $0.00006 $0.00753
Haiku 4.5 $0.00003 $0.00377

Measured 6d ago against content hash bec7ead37641, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 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.

skills/pdlc/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Development Lifecycle

Orchestrates the full PDLC loop by invoking phase skills in sequence. Each phase consumes the previous phase's artifact and ends in a gate (make-decision) with verdict proceed / pivot / kill. Pass an optional phase name to enter the loop at a specific stage.

PDLC wraps SDLC: it decides whether and what to build, hands the how off to SDLC at define-acceptance, then closes the loop with launch and measurement.

When to Use /pdlc vs Individual Skills

  • Use /pdlc (with an optional phase name) when you want the orchestrator to run multiple phases, manage gates and backtracking, and maintain run state. The PDLC phase skills are internal sub-skills bundled under this pdlc skill at skills/pdlc/skills/<name>/SKILL.md. They are not individually discovered as slash commands, so only /pdlc is directly invocable; the orchestrator loads each phase by reading its file (see Load Each Phase Sub-Skill below).

Load Each Phase Sub-Skill (mandatory)

Before performing any work that belongs to a phase, read that phase's sub-skill file at skills/pdlc/skills/<name>/SKILL.md (use the Read tool) so its workflow, gates, and commit rules are in context. Never execute a phase's actions from memory or general knowledge. This applies at every phase transition, on every entry point and fast path. If you reach a phase that commits, pushes, or opens a PR and its sub-skill is not yet read, read it before doing anything else, then follow its workflow.

Loop Overview

The PDLC loop — 6 phases (entry: problem → measure)

  Phase 1 — Discover (divergent: find problems worth solving)
  discover-problems     Synthesize JTBD, interviews, and problem statements
  research-market       Size the market, map trends and segments
  analyze-competition    Map the competitive landscape and positioning gaps
  frame-opportunities    Build an opportunity-solution tree, scored
          │
          ▼  GATE (make-decision: proceed / pivot / kill)
  Phase 2 — Validate (converge or kill, before any build)
  map-assumptions        List hypotheses, beliefs, and risks ranked by leverage
  design-experiment      Design the cheapest decisive test (fake-door, concierge, prototype, survey)
  run-experiment         Execute, collect data, record a verdict
          │
          ▼  GATE (make-decision: proceed / pivot / kill)
  Phase 3 — Strategy (decide where to focus)
  define-vision          Product vision, target customer, positioning
  set-goals              OKRs, success metrics + guardrail metrics
  build-roadmap          Now/Next/Later, outcome-based
  prioritize             Rank the backlog (RICE / WSJF)
          │
          ▼  GATE (make-decision: proceed / pivot / kill)
  Phase 4 — Define (turn outcome into buildable scope)
  write-prd              Problem, outcomes, success criteria, non-goals
  define-acceptance      Acceptance contract: testable criteria (HANDOFF TO SDLC)
  prototype-ux           Wireframes/prototype + usability findings
          │
          ▼  GATE (make-decision: proceed / pivot / kill)  ──►  SDLC owns the build
  Phase 5 — Launch (go-to-market)
  plan-launch            Readiness checklist, timeline, channels
  craft-messaging        Value prop, messaging house, narratives
  enable-teams           Sales playbook, support runbook
  set-pricing            Pricing model, packaging, tiers
          │
          ▼  GATE (make-decision: proceed / pivot / kill)
  Phase 6 — Measure (close the loop)
  spec-analytics         Events, funnels, dashboards, guardrails
  review-metrics         Actuals vs goals, anomalies, health report
  synthesize-feedback    Aggregate support, sales, NPS, reviews
  run-retrospective      Keep / stop / start
  sunset-product         End-of-life plan (when an initiative is net-negative)
          │
          ▼  GATE (make-decision: double-down / iterate / sunset)  ──► feeds back into Discover

Cross-cutting (invoke at any point)

  make-decision          The gate mechanism — one decision record, reused at every transition
  kill-initiative        Explicit sunset-or-pivot: reallocate capacity, notify stakeholders
  brief-stakeholders     Exec summary, status update, stakeholder map
  audit-outcomes         Trace shipped outcomes back to the original problem and metrics (PDLC backpropagation)
  manage-portfolio       Health across multiple initiatives/products

Setup (run once per project, no dependencies on the loop)

  initialize-pdlc-directory   Bootstrap .pdlc/ structure and populate templates
  sync-pdlc                   Reconcile .pdlc/ with current product reality (calls initialize if absent)

Read the full file on GitHub · 249 lines

Files

What ships with it

59 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.

  1. 6d ago First seen · 249 lines · 30 tokens per session scan A bec7ead37641

Subscribe to this mod's changes

pdlc is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 3,765 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens