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/generous-corp/pulp/web-pluginsnpx skills add Generous-Corp/pulp --skill web-pluginsgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote 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/generous-corp/pulp/web-plugins)<a href="https://agentmods.dev/skills/generous-corp/pulp/web-plugins"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/web-plugins.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 | $0.00127 | $0.20153 |
| Opus 5 | $0.00063 | $0.10077 |
| Sonnet 5 | $0.00025 | $0.04031 |
| Haiku 4.5 | $0.00013 | $0.02015 |
Grade B, and why
web-plugins scanned grade B 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 today.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
system GPU. One-time: `sudo safaridriver --enable` + Safari → Develop → "Allow Remote How it starts
The opening of the file, as written. The whole thing — 1,315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pulp on the web (WAM v2 / WebCLAP / browser UI)
Pulp targets the browser through two audio ABIs and one UI host:
| Piece | Where | What it is |
|---|---|---|
| WAM v2 adapter | core/format/src/wasm/wam_adapter.cpp, wam-runtime.mjs |
The whole module lives inside one AudioWorklet |
| WebCLAP adapter | core/format/src/wasm/ + examples/web-demos/wclap-build/ |
Real CLAP, wasm-hosted; needs COOP/COEP for threaded shared memory |
| Browser window host | core/view/platform/web/ |
core/view's widget tree painted by Skia Ganesh on WebGL2 |
The audio side and the UI side are independent. The browser UI module is
DSP-free and talks to audio only through the web player's HostAdapter seam, so
the same wasm UI module mounts against both a WAM and a WebCLAP demo. Build it
once; if it looks different across the two ABIs, that is a shared-player bug, not
a per-demo tweak.
What is NOT in the browser
Be precise about this; it is easy to overclaim and the claims get quoted.
- The UI is not Graphite/Dawn. The published Skia wasm slice is Ganesh on
WebGL2 and ships zero
wgpusymbols (see theskia-gpu-buildskill's wasm section). WebGL2 has no compute shaders, so the UI's render path cannot carry GPU DSP — the two lanes are unrelated (see below). - File-backed loaders and native editors are compiled out (
PULP_WASM/PULP_HEADLESS). A plugin that needs an asset on the web must carry it in the binary or fetch it on the main thread — anAudioWorkletGlobalScopecannot fetch, which is also why the WAM worklet build must beSINGLE_FILE(the wasm embedded in the .js).
GPU audio in the browser: it exists, and it is a THIRD lane
CI capacity isolation. The real-GPU macOS proof is advisory and must not
consume a required merge-gate runner. .github/workflows/web-plugins.yml
therefore reads PULP_ADVISORY_GPU_MACOS_RUNS_ON_JSON, not
PULP_LOCAL_MACOS_RUNS_ON_JSON, and passes it through
tools/scripts/resolve_advisory_macos_runner.py. The proof skips when the
advisory selector is unset; configured selectors must be self-hosted and cannot
contain pulp-build* or pulp-preamble*, and must carry a
pulp-advisory-* identity. Give the proof its own governed tartci supervisor
and pulp-advisory-gpu label. Do not add that advisory label to a required
runner, and do not use Orchard.
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.
- today Changed · +19 lines 914f1dfffb35
- today First seen · 1,296 lines · 127 tokens per session scan B cb02c9f21b8d
web-plugins is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 20,153 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
v8-jit
V8 JIT optimization patterns for writing high-performance JavaScript in Next.js server internals. Use when writing or reviewing hot-path code in app-render, stream-utils, routing, caching, or any per-request code path. Covers hidden classes / shapes, monomorphic call sites, inline caches, megamorphic deopt, closure…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.