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 agentmods add skills/matthewdigiuseppe/mstack/theory-buildnpx skills add matthewdigiuseppe/MStack --skill theory-buildgit clone --depth 1 https://github.com/matthewdigiuseppe/MStackWrote 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/matthewdigiuseppe/mstack/theory-build)<a href="https://agentmods.dev/skills/matthewdigiuseppe/mstack/theory-build"><img src="https://agentmods.dev/badge/skills/matthewdigiuseppe/mstack/theory-build.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.00721 |
| Opus 5 | $0.00033 | $0.00360 |
| Sonnet 5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
theory-build 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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mstack:theory-build
Stage: map Voice: theorist
When to invoke
After /mstack:lit-map so you know the conversation. Before /mstack:hypothesis-design so the hypotheses are derived from a stated mechanism, not retrofitted to results.
Procedure
-
Load.
.mstack/research-question.mdand.mstack/lit-map.md. -
State the mechanism in one sentence. "X causes Y because Z." If the user can't, ask until they can. The sentence is the spine of the paper.
-
Draw the DAG (in prose / ASCII). Nodes:
- The treatment / IV.
- The outcome.
- Mediators (M1, M2, …).
- Pre-treatment confounders (W1, W2, …).
- Post-treatment colliders (C1, …) — flag these explicitly; controlling on a collider is a common error.
Edges with sign and a one-line justification per edge.
Save the DAG to
.mstack/theory.mdas ASCII; the user can rebuild it as a figure later. -
Scope conditions. Three to five sentences:
- Population scope — for whom should this hold?
- Time scope — what era?
- Institutional scope — what kind of state, regime, market?
- Boundary — where would you expect the mechanism to break?
-
Implications. What does this theory predict for cases / observations not in the data? At least two predictions outside the proposed sample. These are the "off-the-line" predictions that distinguish a real theory from a story tuned to the data.
-
Compatibility check with
/mstack:lit-map:- Which Foundation paper(s) does the mechanism build on?
- Which Frontier paper(s) does it dispute?
- Where does the theory stand on the contested edge of the conversation?
-
Save the full theory to
.mstack/theory.md. Optionally stubpaper/sections/theory.texwith the mechanism sentence + scope conditions; full drafting later via/mstack:draft-section theory.
Outputs
.mstack/theory.md— mechanism, DAG, scope, predictions, lit-positioning.- (Optional) stubbed
paper/sections/theory.tex. - Summary block: mechanism sentence + the one off-the-line prediction most likely to falsify.
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.
- 5d ago First seen · 66 lines · 66 tokens per session scan A 6b60754dfca0
theory-build is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 9d ago), licensed MIT. It adds 66 tokens to every session and 721 once invoked, about $0.0003 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.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…