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.
git clone --depth 1 https://github.com/zpyoung/quirkWrote 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/plugins/zpyoung/quirk/quirk)<a href="https://agentmods.dev/plugins/zpyoung/quirk/quirk"><img src="https://agentmods.dev/badge/plugins/zpyoung/quirk/quirk/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/plugins/zpyoung/quirk/quirk"><img src="https://agentmods.dev/badge/plugins/zpyoung/quirk/quirk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
quirk 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 4d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What it installs
The manifest is a name and a version. 31 skills, 2 commands, 3 hooks travel with it, and installing the plugin installs all of them — 2,340 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill subagent-driven-development A 17 tokens
- Skill writing-plans A 52 tokens
- Skill adversarial-review A 115 tokens
- Skill brainstorming A 37 tokens
- Skill full-code-review A 155 tokens
- Skill simplifying-safely A 110 tokens
- Skill writing-skills A 74 tokens
- Skill exploring-ideas A 116 tokens
- Skill using-apps-like-a-user A 122 tokens
- Skill writing-html-artifacts A 115 tokens
- Skill writing-scannable-prose A 112 tokens
- Skill building-mini-apps A 113 tokens
- Skill filing-requests A 118 tokens
- Skill interface-design A 128 tokens
- Skill making-videos A 106 tokens
- Skill pi-dev A 66 tokens
- Skill releasing-quirk A 73 tokens
- Skill systematic-debugging A 21 tokens
- Skill test-driven-development A 17 tokens
- Skill adhd A 66 tokens
- Skill dispatching-parallel-agents A 26 tokens
- Skill executing-plans A 29 tokens
- Skill receiving-code-review A 38 tokens
- Skill stacking-prs A 82 tokens
- Skill using-git-worktrees A 35 tokens
- Skill using-quirk A 30 tokens
- Skill finishing-a-development-branch A 44 tokens
- Skill verification-before-completion A 43 tokens
- Skill requesting-code-review A 22 tokens
- Skill typed-artifacts A 102 tokens
- Skill writing-specs A 65 tokens
- Command explore A 45 tokens
- Command adversarial-review A 46 tokens
- Hook SessionStart A not measured
- Hook PostToolUse A not measured
- Hook Stop A not measured
What ships with it
1 file beside plugin.json 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.
- 4d ago Changed 0bd397754cdc
- 6d ago Changed 3e9d8bc30f10
- 7d ago Changed a5ed9d1f66b3
- 8d ago Changed 8b37e696c5fd
- 15d ago Changed 4105c3eec1a8
- 18d ago Changed 24f3de24c71a
- 20d ago Changed 86667275eb26
- 22d ago Changed 3ccfa3eeac69
- 23d ago Changed e1c5e369cdf4
- 25d ago First seen · 35 lines scan A edd6cbe77aa4
quirk is a plugin published in the GitHub repository zpyoung/quirk (6 stars, last pushed 5d ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
quirk compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| quirkzpyoung/quirk | Plugin | 6 | 5d ago | none | A | — | Claude Code |
| humanizerblader/humanizer | Plugin | 68k | yesterday | MIT | A | — | Claude Code |
| claude-plugins-official marketplaceanthropics/claude-plugins-official | Plugin | 47k | today | Apache-2.0 | A | — | Claude Code |
| nextjsvercel/next.js | Plugin | 143k | today | MIT | A | — | Claude Code |
| themes-examplegoogle-gemini/gemini-cli | Plugin | 109k | today | Apache-2.0 | A | — | Gemini CLI |
| knowledge-work-plugins marketplaceanthropics/knowledge-work-plugins | Plugin | 35k | yesterday | Apache-2.0 | A | — | Claude Code |
| code-modernizationanthropics/claude-plugins-official | Plugin | 47k | today | Apache-2.0 | A | — | Claude Code |