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/mayank-io/mstack/clipnpx skills add mayank-io/mstack --skill clipgit clone --depth 1 https://github.com/mayank-io/mstackWhat 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 | $0.00088 | $0.02529 |
| Opus 5 | $0.00044 | $0.01264 |
| Sonnet 5 | $0.00018 | $0.00506 |
| Haiku 4.5 | $0.00009 | $0.00253 |
Grade A, and why
clip scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| PDF (any host, incl. Drive/Dropbox) | `curl` → `notes:save-local-file` | — | How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clip
Route a URL to the correct extraction skill and note-writer. This skill is a router. It does not format notes and does not know vault conventions — the downstream skill owns that.
Input
The user provided: $ARGUMENTS — a URL, optionally followed by extra instructions (e.g. "tag it to project X", "capture with the edge-idea tag"). Pass extra instructions through to the downstream skill and honour them after it returns.
Step 1 — Identify the source
Match on the URL's host and path.
| Source | Fetch with | Template |
|---|---|---|
youtube.com, youtu.be |
fetch:youtube-transcript |
youtube.md (+ channel override) |
x.com, twitter.com |
fetch:x-post |
x.md |
linkedin.com |
fetch:linkedin-post |
linkedin.md |
*.notion.site, notion.so |
fetch:notion-public-site |
notion.md |
scribd.com |
fetch:scribd-document |
article.md |
alphaxiv.org, arxiv.org |
fetch:alphaxiv-paper |
paper.md |
| PDF (any host, incl. Drive/Dropbox) | curl → notes:save-local-file |
— |
| anything else | fetch:blog-post |
article.md |
The fallback goes to fetch:blog-post, not obsidian:defuddle. blog-post uses Defuddle internally and recovers the lazy-loaded images Defuddle drops, digitizes embedded Vedic charts via fetch:vedic-chart, and emits the same OUTPUT_DIR: contract as every other route. Routing straight to defuddle skips all of that and reaches outside this marketplace for a capability we already own.
Every route is the same six steps. There is no per-source skill, and there should never be one — what varies between sources is output shape, and shape lives in templates/.
1. route on host ──▶ fetch:<source> (curl, for PDF)
2. read its OUTPUT_FILE: / OUTPUT_DIR: final line — Step 2
3. select templates/<source>.md, and templates/channels/<name>.md if one matches
4. if the content is a transcript ──▶ notes:clean-transcript
5. fill the template
6. notes:create (or notes:save-local-file, for PDF)
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.
- yesterday First seen · 161 lines · 88 tokens per session scan A d7a98abc4038
clip is a skill published in the GitHub repository mayank-io/mstack (5 stars, last pushed 7d ago), licensed MIT. It adds 88 tokens to every session and 2,529 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…