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-architecture/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-architecture)<a href="https://agentmods.dev/skills/lukacf/meerkat/meerkat-architecture"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/meerkat-architecture/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-architecture"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/meerkat-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 351 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00082 | $0.11785 |
| Opus 5 | $0.00041 | $0.05893 |
| Sonnet 5 | $0.00016 | $0.02357 |
| Haiku 4.5 | $0.00008 | $0.01179 |
Grade A, and why
meerkat-architecture 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 11d 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 — 697 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meerkat Internal Architecture
Meerkat is a library-first agent runtime. The execution pipeline is shared across all surfaces. Understanding crate ownership, trait contracts, the DSL-authoritative machine system, and the runtime control plane is essential for making changes that don't break architectural invariants.
This file is a lean navigator. Load the specific reference under references/ when working on that domain.
Core Principles
- Infrastructure, not application — the agent loop is a composable primitive with no opinions about prompts, tools, or output.
- Trait contracts own the architecture —
meerkat-coredefines contracts; implementations live in satellite crates. - Surfaces are skins, not authorities — CLI, REST, RPC, MCP, WASM route through shared substrate and factory seams. Runtime semantics (keep-alive, input admission, drain lifecycle, commit boundaries) are owned by the shared runtime control plane (
MeerkatMachineinmeerkat-runtime); runtime-backed surfaces lower into it, they do not own it. - Composition over configuration — optional components are
Option<Arc<dyn Trait>>, not feature-flagged defaults. - Runtime conforms to catalog-generated machines — the runtime follows the verified DSL model, not the other way around. Production bridge modules import/invoke catalog-owned DSL bodies; they do not author competing machine semantics.
- Mob is the only multi-agent runtime path — no separate sub-agent substrate. User-facing "delegate"/"sub-agent" flows compile to mob members, often inside session-owned implicit mobs.
- Override-first resource injection —
AgentBuildConfigoverrides take precedence over factory/config/filesystem resolution. - Seams are formal — async owner handoffs, wait barriers, and surfaced terminal classes are modeled in the DSL or composition protocols, not left to shell convention.
- Parity gates are dogmatic — production/catalog schema drift, command alphabet drift, string whitelists, and handwritten production machine bodies are CI failures, not review notes.
What ships with it
7 files 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.
- 11d ago First seen · 697 lines · 82 tokens per session scan A 64b30fc49200
meerkat-architecture is a skill published in the GitHub repository lukacf/meerkat (20 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 11,785 once invoked, about $0.0004 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
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-shell.
agent-reproduce-feature
Use when reproducing an existing Codex or Claude Code feature in Qwen Code or another agent CLI by choosing a reference agent, capturing HTTP request bodies, prompts, tool/function schemas, terminal output, and then implementing the matching behavior in the target repo.
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.