prismstack CLAUDE.md

A developer handoff guide for Prismstack, a tool that builds domain-specific packs of Claude Code skills from the gstack methodology.

In plain words
What is it for?
Use it when installing, testing, creating, or maintaining Prismstack skill packs.
Why use it?
It documents the project layout, installation, testing, skill-file format, language rules, and commit style needed for consistent changes.

Instructions file

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 instructions/fagemx/prismstack/claude-md
Clone the repo
git clone --depth 1 https://github.com/fagemx/prismstack
Per session 303 This file is loaded in full into every session.
When invoked 303 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00303 $0.00303
Opus 5 $0.00151 $0.00151
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00030 $0.00030

Measured 2d ago against content hash 04a949ae8c21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prismstack CLAUDE.md 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 2d 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.md · 66 lines

What it actually says

Prismstack — Developer Handoff

Project Overview

Prismstack is a 10-skill domain stack builder tool, installed as Claude Code skills. It takes gstack methodology and produces domain-specific skill packs. Skills are installed to ~/.claude/skills/prismstack/.

Directory Structure

prismstack/
  skills/       # Skill definition files (YAML frontmatter + Markdown body)
  bin/           # Executable scripts (install, helpers)
  docs/          # Documentation and reference materials
  test/          # Test scripts

Installation

bash bin/install.sh

Testing

bash test/install-test.sh

Skill Format

Each skill file uses YAML frontmatter followed by a Markdown body:

---
name: skill-name
version: 0.1.0
origin: prismstack
description: What this skill does
allowed-tools:
  - Bash
  - Read
  - Write
---

# Skill Title

Skill instructions in Markdown...

Commit Style

Use conventional commits:

  • feat: — new feature or skill
  • fix: — bug fix
  • docs: — documentation changes

Language

  • Skill content: 繁體中文
  • Code and comments: English

Reference Materials

gstack knowledge base is located at: C:\ai_project\guardian\docs\tech\gstack\

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. 2d ago First seen · 66 lines · 303 tokens per session scan A 04a949ae8c21

Subscribe to this mod's changes

prismstack CLAUDE.md is an instructions file published in the GitHub repository fagemx/prismstack (2 stars, last pushed 4mo ago), licensed MIT. It adds 303 tokens to every session, about $0.0015 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 2026-08-31.