Borrowing it
Nothing to install: this file belongs to lukacf/meerkat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lukacf/meerkat/main/.claude/skills/meerkat-wasm/SKILL.mdgit clone --depth 1 https://github.com/lukacf/meerkatWrote 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/lukacf/meerkat/meerkat-wasm)<a href="https://agentmods.dev/skills/lukacf/meerkat/meerkat-wasm"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/meerkat-wasm/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/lukacf/meerkat/meerkat-wasm"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/meerkat-wasm.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 | $0.00136 | $0.05181 |
| Opus 5.5 | $0.00054 | $0.02072 |
| Sonnet 5.5 | $0.00027 | $0.01036 |
| Haiku 4.5 | $0.00014 | $0.00518 |
Grade A, and why
meerkat-wasm 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 13d 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meerkat WASM Embedded Runtime
The meerkat-web-runtime crate compiles the full meerkat agent stack to wasm32-unknown-unknown. It is an embedded deployment target for mobpacks — the JavaScript equivalent of the Rust SDK. Not a protocol server like RPC/REST.
The crate is not published to crates.io (publish = false); browser hosts
consume it as the prebuilt WASM inside @rkat/web.
Crate Compatibility Pattern
To make a meerkat crate compile for wasm32, apply this pattern:
Cargo.toml — gate platform-specific deps:
[target.'cfg(not(target_arch = "wasm32"))'.dependencies]
tokio = { workspace = true }
rusqlite = { workspace = true }
[target.'cfg(target_arch = "wasm32")'.dependencies]
tokio_with_wasm = { workspace = true }
lib.rs - tokio alias + module gating:
#[cfg(target_arch = "wasm32")]
pub mod tokio {
pub use meerkat_core::time_compat::wasm as time;
pub use meerkat_core::tokio::spawn;
pub use meerkat_core::tokio::task;
pub use tokio_with_wasm::alias::*;
}
#[cfg(not(target_arch = "wasm32"))]
mod filesystem_module;
async_trait — dual cfg_attr:
#[cfg_attr(target_arch = "wasm32", async_trait(?Send))]
#[cfg_attr(not(target_arch = "wasm32"), async_trait)]
Time types — use meerkat_core::time_compat::{SystemTime, Instant, Duration}, never std::time::*.
Tokio imports in wasm32-visible code — add #[cfg(target_arch = "wasm32")] use crate::tokio; then existing use tokio::... paths resolve through the alias.
Use the shared core alias for WASM scheduling. Its time adapter owns the exact
JavaScript timer handle and cancels it when the Rust future is dropped. Direct
tokio_with_wasm::alias::time calls bypass that cleanup. The shared task alias
also implements yield_now through the same cancellable timer. Its spawn and
task::JoinSet box every future before handing it to tokio_with_wasm, which
keeps spawn-wrapper shadow-stack frames small; route spawns through the alias,
not tokio_with_wasm::spawn. The SDK's release build fails when a spawn-wrapper
frame exceeds 8 KiB (sdks/web/scripts/wasm-frames.mjs). Native code continues
to use Tokio. Lifecycle tests must exit naturally after teardown; forcing a
successful Node exit hides retained timer resources.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago Changed · +46 lines scan B → A 1d27a6de590b
- 1mo ago Changed · +42 lines e2d6da6ea782
- 1mo ago Changed 0ff977f4a7ab
- 1mo ago Changed · +22 lines aecbf02474a9
- 1mo ago Changed db4ecef6a68e
- 1mo ago First seen · 201 lines · 136 tokens per session scan B 119501fdda00
meerkat-wasm is a skill published in the GitHub repository lukacf/meerkat (23 stars, last pushed today), licensed Apache-2.0. It adds 136 tokens to every session and 5,181 once invoked, about $0.0005 per session on Opus 5.5. 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
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop.
batch-api
Prepare a many-file, single-turn transform (translate, rewrite, extract) as a plan and submit it to the asynchronous, half-price DashScope Batch API; results are delivered as new files hours later. Invoke explicitly with /batch-api.
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.