What is ghm-self-install?

An installer for adding the PRD-Driven Context Engineering framework to a new or existing repository. It adds agent instructions, hooks, skills, agents, rules, and scripts without replacing the project's product files.

Use it to install the framework, choose an installation mode, verify that hooks emit valid JSON, and run the readiness check.

It provides a repeatable way to install the framework while protecting files such as PRD.md, README.md, MEMORY.md, and source-of-truth content. It runs through the user's Claude Code subscription without requiring a separate API service.

ghm-self-install — Skill for Claude Code by mattgierhart

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 mattgierhart/PRD-driven-context-engineering --skill ghm-self-install

Clone the repo

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

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/ghm-self-install.svg)](https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/ghm-self-install)

Your own site

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

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,006 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.

Model	Per session	Once invoked
Fable 5.1	$0.00105	$0.01006
Opus 5	$0.00053	$0.00503
Sonnet 5	$0.00021	$0.00201
Haiku 4.5	$0.00011	$0.00101

Measured 9d ago against content hash aed06649757b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ghm-self-install 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 9d 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/ghm-self-install/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Install

Install the methodology into a target repo from the install manifest, the way Xantham's blueprint installs from markdown: the agent runtime is the installer, so the whole thing runs inside your Claude Code subscription — no API key, no metered calls, no service to stand up.

Two paths, one manifest. This skill is the interactive path. install.sh is the deterministic CLI path. Both read .claude/install-manifest.yaml, so they can't drift. Prefer driving install.sh from this skill; fall back to manual copies only when the script isn't reachable.

Consumes

.claude/install-manifest.yaml — authoritative framework / template_seed / never_touch lists (the keystone; never hardcode file lists).
install.sh — the deterministic installer this skill normally drives.
Safety rules from ghm-template-sync Phase "Safety Rules" — never overwrite MEMORY.md, SoT/*, PRD.md, README.md content.

Produces

An installed framework in the target repo (no new SoT IDs — this skill places the engine, it doesn't author specs).
A verification report (hooks emit valid JSON; readiness.py runs).

Workflow

Phase 1 — Preflight & mode detect

Confirm git, python3, awk are present; warn if the target isn't a git repo.
Detect mode: greenfield (no .claude/) vs brownfield (existing .claude/). Brownfield means merge, never overwrite product.
State the trade explicitly: this installs files only — it costs subscription tokens for the wizard turn, zero API.

Phase 2 — Wizard questions

Ask only what changes the outcome (honor the execution mode's budget):

Target directory (default: current repo).
Domain profile: product (default) · library · infrastructure · research.
Subset [standard+]: keep all 4 agents + all skills (default), or trim to a role subset. Quick mode skips this and installs everything.

Phase 3 — Install (drive `install.sh`)

Run the deterministic installer so behavior matches the CLI path exactly:

bash install.sh --target <DIR> --profile <PROFILE>        # add --dry-run to preview

Show the --dry-run plan first [standard+], then execute.
If a framework file shows drift, surface the diff and only re-run with --force after the user confirms (mirrors ghm-template-sync "show diff before destructive").
Never write anything in the manifest's never_touch list.

Read the full file on GitHub · 90 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.

9d ago First seen · 90 lines · 105 tokens per session scan A aed06649757b

Subscribe to this mod's changes

ghm-self-install is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 8d ago), licensed MIT. It adds 105 tokens to every session and 1,006 once invoked, about $0.0005 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.

Building agents Claude Code agent-skills agentic-coding ai-agents ai-assisted claude

ralplan

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.

Yeachan-Heo/oh-my-claudecode · 21 tokens

remember

Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.

Yeachan-Heo/oh-my-claudecode · 20 tokens

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

explaining-machine-learning-models

Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.

foryourhealth111-pixel/Vibe-Skills · 49 tokens

aiwg-regenerate-copilot

Regenerate copilot-instructions.md for GitHub Copilot with vendor-specific content only.

jmagly/aiwg · 25 tokens