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/yuchi-chang/no-capeWrote 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/yuchi-chang/no-cape/no-cape)<a href="https://agentmods.dev/plugins/yuchi-chang/no-cape/no-cape"><img src="https://agentmods.dev/badge/plugins/yuchi-chang/no-cape/no-cape/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/yuchi-chang/no-cape/no-cape"><img src="https://agentmods.dev/badge/plugins/yuchi-chang/no-cape/no-cape.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
no-cape 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 22d 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. 15 skills, 1 command, 3 hooks travel with it, and installing the plugin installs all of them — 458 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill clarifying-requirements A 30 tokens
- Skill exploring-approaches A 36 tokens
- Skill durable-plans A 40 tokens
- Skill escalate-dont-thrash A 31 tokens
- Skill verify-before-done A 40 tokens
- Skill writing-meaningful-tests A 26 tokens
- Skill blast-radius A 29 tokens
- Skill fail-loud A 30 tokens
- Skill receiving-feedback A 23 tokens
- Skill root-cause-debugging A 30 tokens
- Skill safe-refactoring A 25 tokens
- Skill schema-migration-safety A 28 tokens
- Skill surgical-changes A 28 tokens
- Skill writing-solid-plans A 23 tokens
- Skill measure-before-optimizing A 23 tokens
- Command no-cape A 16 tokens
- Hook SessionStart A not measured
- Hook UserPromptSubmit 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.
- 22d ago Changed 48a814083060
- 2mo ago First seen · 23 lines scan A 6341e231c188
no-cape is a plugin published in the GitHub repository yuchi-chang/no-cape (2 stars, last pushed 24d 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.
Other plugins, from other repositories
vibe-ship
Dockerize and deploy any app: detects the stack (Node, Next.js, Python, Django, FastAPI, Go, Rust, Java/Spring, .NET, Rails, Laravel, Phoenix, static, monorepos), writes hardened Dockerfiles, Compose, GitHub Actions/GitLab CI, Kubernetes and Fly/Render/Railway/Cloud Run/AWS/VPS configs, then verifies them with a…
claude-math
Render math legibly in Claude Code (and OpenAI Codex CLI, via the same SKILL.md). Emits Unicode glyphs instead of unrenderable LaTeX in Unicode-capable terminals. A stopgap until hosts render math natively.
documentation-plugin
Plugin for writing, maintaining, and cleaning technical documentation.
claude-unlimited
Orquestador multi-agente que, a partir de un prompt, corre el loop plan → code → QA → review → iterar sobre un gateway local OpenAI-compatible (OmniRoute). Sirve para proyectos de software de cualquier tipo (frontend, backend, CLIs, scripts, librerías, config); el QA visual con la skill websight es OPCIONAL y lo…
shumo-paper
A Chinese-language assistant for the National College Students Mathematical Modeling Competition. It covers problem analysis, model selection, data preparation, solving, result checks, and writing the competition paper.
superpowers-graph
The Superpowers software-development methodology executed as a guarded state machine: 21 typed nodes, 96 total exit guards, 9 bounded retry loops, durable run state that survives compaction, and a ledger recording every step that could not run.