A starter workflow for a new, empty software repository using a PRD, or product requirements document, as the central plan. It creates templates for project knowledge, work epics, domain settings, and agent memory.

Use it to seed a greenfield repository with PRD.md, SoT files, epic templates, domain configuration, and starter memory files.

It gives a new project a consistent structure for recording requirements and shared context. It does not adapt an existing project that already contains PRD or SoT content; SoT means the project's source-of-truth knowledge files.

init — Skill for Claude Code and Codex by mattgierhart: A starter workflow for a new, empty software repository…

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 skills/mattgierhart/prd-driven-context-engineering/init

Any agent

npx skills add mattgierhart/PRD-driven-context-engineering --skill init

Clone the repo

git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering

Made for: Claude Code, 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/mattgierhart/prd-driven-context-engineering/init.svg)](https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/init)

Your own site

<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/init"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/init.svg" alt="Measured on agentmods" height="20"></a>

Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,250 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00130	$0.01250
Opus 5	$0.00065	$0.00625
Sonnet 5	$0.00026	$0.00250
Haiku 4.5	$0.00013	$0.00125

Measured 3d ago against content hash 9a768e495da9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 3d 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.

.claude/skills/init/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prd-ce:init — Greenfield Scaffold Seeder

Plant the consumer-owned scaffold for a fresh PRD-CE project. The methodology engine (lifecycle skills, the agent squad, governance hooks, readiness.py) is delivered live by the installed prd-ce plugin — it never gets copied into your repo. This skill seeds only what is yours to own and edit: PRD.md, the SoT/ graph, epics/ templates, your .claude/domain-profile.yaml, and per-agent MEMORY.md starters.

One manifest, no drift. The seed list comes from install-manifest.yaml's template_seed section — the same list install.sh (fork path) and ghm-template-sync (update path) read. This skill drives the deterministic prd-ce-init.sh so behavior is identical no matter who invokes it.

Scope (v1): greenfield only. This seeds an empty structure into a fresh repo. Mid-build and live-codebase on-ramps (entry-mode branching, graph extraction) are backlogged — see temp/plugin-conversion-plan.md. If the target already has PRD.md or SoT/ content, the seeder keeps it (non-destructive) rather than adapting to it.

Consumes

${CLAUDE_PLUGIN_ROOT}/templates/ — the bundled seed sources (mirrors template_seed paths) the packager ships with the plugin.
install-manifest.yaml template_seed + never_touch — authoritative seed/skip lists.
scripts/prd-ce-init.sh — the deterministic seeder this skill drives.

Produces

A seeded scaffold in the target repo (no new SoT IDs — this skill places templates, it does not author specs).
A freshly reset PRD.md (frontmatter at v0.1, today's date, no stale template_version).
A verification report (hooks emit valid JSON; readiness.py runs).

Workflow

Phase 1 — Preflight

Confirm git, python3, bash are present. Warn (don't block) if the target isn't a git repo.
Confirm greenfield: if PRD.md or non-empty SoT/ already exist, say so and stop — the seeder will keep them untouched, so there is nothing for init to do. (Point the user at the lifecycle skills to keep building, not at re-seeding.)

Read the full file on GitHub · 97 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.

3d ago First seen · 97 lines · 130 tokens per session scan A 9a768e495da9

Subscribe to this mod's changes

init is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 3d ago), licensed MIT. It adds 130 tokens to every session and 1,250 once invoked, about $0.0006 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.

Memory and context agent-skills agentic-coding ai-agents ai-assisted claude claude-code

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

foryourhealth111-pixel/Vibe-Skills · 37 tokens

docx-comment-reply

Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.

foryourhealth111-pixel/Vibe-Skills · 39 tokens

spec-kitty-charter-doctrine

Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…

Priivacy-ai/spec-kitty · 135 tokens

oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…

first-fluke/oh-my-agent · 73 tokens

oma-hwp

Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.

first-fluke/oh-my-agent · 59 tokens

moai-ref-ui-polish

UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…

modu-ai/moai-adk · 98 tokens