Stage_Manager_Skills: Instructions file for Claude Code

CLAUDE.md

Stage_Manager_Skills CLAUDE.md is an instructions file for Claude Code from mnfst-ai/Stage_Manager_Skills. It costs 835 tokens per session, scanned A, original, MIT.

A library of 16 skills for people who build software with coding agents such as Claude Code, Cursor, or Replit.

In plain words
What is it for?
Use its commands to find gaps, uncover hidden decisions, rank risks, validate the concept, split work into manageable pieces, and prepare a build brief.
Why use it?
It gives a structured process for checking an idea and its risks before building, then planning and reviewing the work afterward.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is mnfst-ai/Stage_Manager_Skills's own configuration. It tells Claude Code how to work on Stage_Manager_Skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Stage_Manager_Skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mnfst-ai/Stage_Manager_Skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mnfst-ai/Stage_Manager_Skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mnfst-ai/Stage_Manager_Skills

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 Stage_Manager_Skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mnfst-ai/stage_manager_skills/claude-md/github.svg)](https://agentmods.dev/instructions/mnfst-ai/stage_manager_skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mnfst-ai/stage_manager_skills/claude-md"><img src="https://agentmods.dev/badge/instructions/mnfst-ai/stage_manager_skills/claude-md/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 Stage_Manager_Skills CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mnfst-ai/stage_manager_skills/claude-md"><img src="https://agentmods.dev/badge/instructions/mnfst-ai/stage_manager_skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 835 This file is loaded in full into every session.
When invoked 835 The same file — it is already loaded in full.
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 $0.00835 $0.00835
Opus 5 $0.00417 $0.00417
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00084 $0.00084

Measured 8d ago against content hash 1917ac9b0550, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Stage_Manager_Skills 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 8d 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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stage Manager — Artful Making Skill Library

A collection of 16 skills for vibe coders who use agentic coding tools (Claude Code, Cursor, Replit). Skills are organized across the Shape-to-Stage flow cycle, including premise validation before building. The mirror never goes dark.

Available Slash Commands

Shape (analyze before building)

  • /sm:shape:find-holes — Find specification gaps where coding tools will invent behavior
  • /sm:shape:collapsed-options — Find decisions made before the builder knew they were making them
  • /sm:shape:risk-sequence — Surface load-bearing assumptions and sequence by cost-if-wrong
  • /sm:shape:soul-check — Deep read on whether the original animating idea is still alive
  • /sm:shape:brief — Synthesize shape skill output into ranked top-three problems, inline change suggestions, Stage_Manager_Brief.md, and [Spec_Name]-Staged.md — the handoff to CE or Superpowers

Transition

  • /sm:shape:gate — Five readiness questions before crossing from shaping to staging

Stage (before, during, and after the build)

  • /sm:stage:chunking — Break work into flow-cycle-sized pieces sequenced by cost of delay (economic, risk, flow, joy)
  • /sm:stage:prompt-craft — Turn shaped chunks into scoped, guardrailed prompts
  • /sm:stage:live-mirror — Compare plan vs. code output per-session, surface what the tool invented
  • /sm:stage:decision-capture — Full decisions-made manifest after a build, feeds forward into learning

Validate (before you build, prove the premise)

  • /sm:yagni — Gate: challenge the premise before a single line of code
  • /sm:invalidate-prep — Surface and rank assumptions, identify personas, generate problem statements
  • /sm:invalidate-interview — Generate a live interview script using negative framing to kill assumptions
  • /sm:invalidate-score — Score each assumption as validated, invalidated, or still open

Any Node

  • /sm:coherence-check — Lightweight 2-minute gate at any transition point mid-build. For the shape/stage boundary, use /sm:shape:brief instead.
  • /sm:stage-manage — Session opener and orchestrator. Watches for signals and suggests skills as they emerge.

Read the full file on GitHub · 61 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. 8d ago First seen · 61 lines · 835 tokens per session scan A 1917ac9b0550

Subscribe to this mod's changes

Stage_Manager_Skills CLAUDE.md is an instructions file published in the GitHub repository mnfst-ai/Stage_Manager_Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 835 tokens to every session, about $0.0042 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens