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/scribd-documentnpx skills add mayank-io/mstack --skill scribd-documentgit 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 | $0.00045 | $0.00746 |
| Opus 5 | $0.00023 | $0.00373 |
| Sonnet 5 | $0.00009 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
scribd-document scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Download Scribd Document
Download all page images from a Scribd document via its embed view.
Browser — always gstack, never headless
Browser work goes through the gstack browser, which holds the user's logged-in sessions. A fresh Playwright instance is logged out: it silently returns login walls or truncated content that looks like a successful capture.
B="$HOME/.claude/skills/gstack/browse/dist/browse"
"$B" connect # run from the target directory — another cwd spawns a second
# daemon and kills the headed session
"$B" goto "<url>"
"$B" js '<expression>'
Do NOT disconnect when done. browse disconnect tears down the daemon and
the logged-in sessions with it. Leave it running — the daemon is a shared user
resource, connect is safe to call again, and only whoever started it should
close it.
Never launch a headless browser. Not headless=True, not --headless, not a
fresh chromium.launch(). If gstack is unavailable, stop and say so rather than
falling back — a logged-out capture is worse than no capture, because it looks fine.
Arguments
$ARGUMENTSshould contain:<url> [output_dir]
Instructions
Run the Scribd extractor script with a 10-minute timeout (large documents can take several minutes to scroll and download):
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/scribd_extractor.py $ARGUMENTS
IMPORTANT: When running this via the Bash tool, set timeout: 600000 (10 minutes).
If httpx or playwright are not installed, install them first:
pip3 install httpx playwright
python3 -m playwright install chromium
The script handles everything:
- Converts the Scribd URL to its embed form (
/embeds/{id}/content) - Drives the gstack browser (headed, via
_browse.py) to the embed — never a headless instance, which would return a login wall for any gated document - Reads the toolbar to detect total page count
- Scrolls through the document to trigger lazy loading of all pages
- Runs targeted scrolling passes for any pages that didn't load
- Downloads all page images as zero-padded
.jpgfiles
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 · 85 lines · 45 tokens per session scan A c340a755483d
scribd-document is a skill published in the GitHub repository mayank-io/mstack (5 stars, last pushed 7d ago), licensed MIT. It adds 45 tokens to every session and 746 once invoked, about $0.0002 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.
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…