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 matthewdigiuseppe/MStack --skill r-and-rgit 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/r-and-r)<a href="https://agentmods.dev/skills/matthewdigiuseppe/mstack/r-and-r"><img src="https://agentmods.dev/badge/skills/matthewdigiuseppe/mstack/r-and-r/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/matthewdigiuseppe/mstack/r-and-r"><img src="https://agentmods.dev/badge/skills/matthewdigiuseppe/mstack/r-and-r.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 | $0.00055 | $0.01027 |
| Opus 5 | $0.00028 | $0.00513 |
| Sonnet 5 | $0.00011 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
r-and-r 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mstack:r-and-r
Stage: submit (R&R) Voice: editor (calibrated as the author addressing the editor and reviewers)
When to invoke
You have a decision letter from the journal. The paper has been revised. Now you need to write the response that gets it across the line — not the response that argues with the reviewer.
Argument
$ARGUMENTS (optional) — round number. Default r1. Use r2, r3 for subsequent rounds.
Procedure
-
Load the decision letter.
- Ask the user to paste the editor's letter and the reviewer reports into
submission/response-to-reviewers/r<N>-decision.mdif not already there. - Read that file. If the file is empty, stop and ask the user for the letter.
- Ask the user to paste the editor's letter and the reviewer reports into
-
Load the manuscript and the diff.
- Read current
paper/main.tex+paper/sections/. - If git is in use, run
git log --since="<date of submission>" --stat -- paper/to know what actually changed. - Read
output/tables/andoutput/figures/— these may have changed.
- Read current
-
Parse the comments. Build a structured list:
- Editor comments (top-level, then specific).
- For each reviewer: comments numbered as the reviewer numbered them.
- Tag each comment as
Major,Minor, orEditor.
-
For each comment, draft a response. Each response has three parts, in order:
- Quote the comment verbatim (in italics or a blockquote). This forces alignment between what the reviewer said and what you address.
- Respond. Concede where conceding is right; defend where defending is right; do not concede the contribution to placate. Use "we appreciate / we agree / we have addressed this by …" sparingly — the structure is enough; you don't need to thank every comment.
- Point to the change. Cite the section, page (or paragraph), and quote the relevant new text. If no change was made, say so explicitly and explain why.
-
Editor opener. A short cover paragraph at the top:
- Thank the editor and reviewers (briefly, once).
- Summarize the most consequential changes (3 bullets).
- Note the structure of the response document.
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.
- 8d ago First seen · 82 lines · 55 tokens per session scan A f49b51293a97
r-and-r is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 12d ago), licensed MIT. It adds 55 tokens to every session and 1,027 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…