initialize-pdlc-directory

initialize-pdlc-directory is a skill for Claude Code from tomzx/agents. It costs 27 tokens per session (964 once invoked), scanned A, original, MIT.

A setup process that creates a standard `.pdlc` folder for product-development work, including places for initiatives, decisions, learnings, context, and templates. PDLC means product development life cycle, the stages used to take an idea from discovery through launch and measurement.

In plain words
What is it for?
Use it to bootstrap the product-work directory and populate missing folders and default templates.
Why use it?
It gives a project a consistent place to store product-planning records without overwriting files that already exist.

Skill for Claude Code

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

Good fit Use it to bootstrap the product-work directory and populate missing folders and default templates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/initialize-pdlc-directory
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 initialize-pdlc-directory
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 initialize-pdlc-directory

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/initialize-pdlc-directory"><img src="https://agentmods.dev/badge/skills/tomzx/agents/initialize-pdlc-directory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 964 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00964
Opus 5 $0.00014 $0.00482
Sonnet 5 $0.00005 $0.00193
Haiku 4.5 $0.00003 $0.00096

Measured 6d ago against content hash 300046bb0e6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

initialize-pdlc-directory 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/skills/initialize-pdlc-directory/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize PDLC Directory

Creates the .pdlc/ directory structure in the project root (or $1 if provided) and populates it with default templates. Already-existing files are never overwritten — safe to run on a project that has partially adopted the structure.

Prerequisites

  • Apply the shared PDLC conventions in skills/pdlc/references/shared.md.
  • Write access to the project root.
  • The canonical templates at ../../templates/ relative to this skill file (i.e. skills/pdlc/templates/).

Steps

  1. Determine the project root: use $1 if provided, otherwise the current working directory.
  2. Resolve the PDLC write location per pdlc/references/shared.md: default <project-root>/.pdlc/; if it cannot be created and PDLC_DIR is set, use $PDLC_DIR/{owner}/{repository}/.pdlc/; mirror created files when set. Record which location was used.
  3. Create each directory below (under the resolved write location) if it does not already exist:
    .pdlc/
    .pdlc/context/
    .pdlc/initiatives/
    .pdlc/decisions/
    .pdlc/learnings/
    .pdlc/templates/
    .pdlc/templates/initiatives/
    .pdlc/templates/context/
    
  4. Create .pdlc/.gitignoreonly if it does not already exist — to keep local-only workflow state out of version control:
    # Local-only workflow state — do not commit
    # Orchestrator run state
    state.yml
    # Per-initiative progress tracking and session logs
    initiatives/*/progress.md
    
    state.yml and each initiative's progress.md are regenerated per machine and per run, so they must never be committed. The initiatives/*/progress.md pattern ignores only the per-initiative files, not the template. Only the repo's .pdlc/.gitignore is meaningful; do not create one under the PDLC_DIR mirror.
  5. For each canonical template file (read from ../../templates/ relative to this skill), copy it to the corresponding path under .pdlc/templates/only if the destination file does not already exist. The templates are the initiative artifacts (under initiatives/), the decision and learning templates, and the context templates (under context/).
  6. For each context file below, create it under .pdlc/context/only if it does not already exist — using the corresponding canonical template (from ../../templates/context/) as starting content:
    • product-overview.md
    • vision.md
    • goals.md
    • roadmap.md
    • vocabulary.md
  7. Write the PDLC anchor to the repo's primary agent-instruction file, per pdlc/references/shared.md (AGENTS.md PDLC anchor). This injects a short, marker-delimited ## PDLC section into AGENTS.md (creating AGENTS.md if it doesn't exist). The block is idempotent: create if absent, replace its delimited content if the markers exist, never touch content outside the markers. Note the target file and whether it was created, updated, or skipped in the report.
  8. Report what was created and what was skipped (already existed). When PDLC_DIR is set, note whether each path was written to the repo, the mirror, or both.

Read the full file on GitHub · 75 lines

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 · 75 lines · 27 tokens per session scan A 300046bb0e6b

Subscribe to this mod's changes

initialize-pdlc-directory is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 964 once invoked, about $0.0001 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