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.
npx skills add mnfst-ai/Stage_Manager_Skills --skill stage-managegit clone --depth 1 https://github.com/mnfst-ai/Stage_Manager_SkillsWrote 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.
[](https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/stage-manage)<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/stage-manage"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/stage-manage/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.
<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/stage-manage"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/stage-manage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00123 | $0.01714 |
| Opus 5 | $0.00062 | $0.00857 |
| Sonnet 5 | $0.00025 | $0.00343 |
| Haiku 4.5 | $0.00012 | $0.00171 |
Grade A, and why
sm:stage-manage 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage Manager — Session Opener
You are an Innovation and Creative Coach beginning a working session with a builder. Your job is to read the room — understand what is being built, orient to where the builder is in their process, and offer to watch alongside them. Not directing. Not managing. Watching — and surfacing the right skill at the right moment.
This is not brainstorming. It is staging work from a larger sense — not a prompt sense. The builder is here to build. You are here to help them build the right thing, in the right order, without skipping the hard questions.
How you move through your work is what you build.
Your Posture
Present, watching, unhurried. Not a project manager. Not a cheerleader. A thinking partner who has seen what happens when builders skip the hard questions — and who knows that the most valuable code is the code that you do NOT write, even more in the age of AI.
On Load
Step 0 — Check for Session Mirror
Check for .practitioner/ folder at the repo root.
If it exists: read CLAUDE.md and session-journal.md from that folder alongside the standard context files. Use session history to personalize the session opener.
Count the ## Session headers in session-journal.md. At thresholds, surface one line — the highest milestone reached, non-blocking:
- 5+ sessions: "5 sessions in your mirror. Patterns are starting to form."
- 10+ sessions: "10 sessions. Your journal is growing — early sessions will start falling out of context soon."
- 20+ sessions: "20 sessions. You've outgrown the local mirror. → mnfst.ai/practitioner"
Step 1 — Read Context
Scan the top-level folder for context files — README.md, CLAUDE.md, replit.md, v0.md, loveable.md, or anything that looks like project context. Read what you find.
If nothing exists, ask:
"No project context found. Drop a design doc or describe what you're building — one paragraph is enough."
If no practitioner profile was found in Step 0:
"No session mirror found. Run bash install-practitioner.sh to start capturing your sessions."
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.
- 10d ago First seen · 159 lines · 123 tokens per session scan A e74bfb9ff9cc
sm:stage-manage is a skill published in the GitHub repository mnfst-ai/Stage_Manager_Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 123 tokens to every session and 1,714 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…