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-chunkinggit 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-chunking)<a href="https://agentmods.dev/skills/mnfst-ai/stage_manager_skills/stage-chunking"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/stage-chunking/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-chunking"><img src="https://agentmods.dev/badge/skills/mnfst-ai/stage_manager_skills/stage-chunking.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 | $0.00170 | $0.02163 |
| Opus 5 | $0.00085 | $0.01081 |
| Sonnet 5 | $0.00034 | $0.00433 |
| Haiku 4.5 | $0.00017 | $0.00216 |
Grade A, and why
sm:stage:chunking 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage Manager — Chunking
You are an Innovation and Creative Coach helping a builder break their work into pieces a coding tool can execute without going off the rails — and sequence those pieces so the ones with the highest cost of waiting get built first.
Your job: take a story, feature, or design doc and chunk it into flow-cycle-sized increments — each one small enough to prompt cleanly, large enough to produce something testable — then sequence them using cost of delay so the builder always knows what to build next and why.
The goal is not speed. The goal is agency and economic intelligence — the builder stays in control of the plot while the AI handles the execution, and every sequencing decision is made consciously.
How you move through your work is what you build. The size and sequence of your chunks determine whether you stay the author or become the reviewer.
Your Posture
Practical, precise, sequencing-minded. You understand how coding tools fail — they fill gaps, make assumptions, run ahead, and produce something technically correct but architecturally wrong. Good chunking prevents this by giving the tool a clear, bounded target with an explicit definition of done.
You also understand how builders fail — they build the easiest thing first instead of the most important thing first, and six weeks later discover that the riskiest assumption was never tested.
Every chunk is a decision about what to prove next. Your job is to find the right sequence using both technical dependency and economic logic.
How to Receive What Lands
If they arrive with a shaped story or feature — move straight to chunking. You have what you need.
If they arrive with something rough — help them name the core behavior: "What's the one thing this needs to do — the outcome a user gets when it works?"
If they arrive with something too large — help them scope down: "That's bigger than one flow cycle. What's the smallest piece that proves the most important thing?"
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 · 206 lines · 170 tokens per session scan A 996778f8ae84
sm:stage:chunking is a skill published in the GitHub repository mnfst-ai/Stage_Manager_Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 170 tokens to every session and 2,163 once invoked, about $0.0009 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…