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/pvillega/claude-templatesWrote 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/pvillega/claude-templates/ct)<a href="https://agentmods.dev/plugins/pvillega/claude-templates/ct"><img src="https://agentmods.dev/badge/plugins/pvillega/claude-templates/ct/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/pvillega/claude-templates/ct"><img src="https://agentmods.dev/badge/plugins/pvillega/claude-templates/ct.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ct 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 2mo 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
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What it installs
The manifest is a name and a version. 38 skills, 7 agents, 7 hooks travel with it, and installing the plugin installs all of them — 5,382 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill opentelemetry A 184 tokens
- Skill argocd A 140 tokens
- Skill coolify A 143 tokens
- Skill kubernetes A 159 tokens
- Skill systemd A 142 tokens
- Skill c-language A 128 tokens
- Skill golang A 137 tokens
- Skill grafana A 148 tokens
- Skill lint-guard A 56 tokens
- Skill redis A 148 tokens
- Skill sqlite-wal A 126 tokens
- Skill terraform-opentofu A 149 tokens
- Skill threat-modeling A 117 tokens
- Skill tls-openssl A 143 tokens
- Skill uv-python A 154 tokens
- Skill dast-scan A 149 tokens
- Skill dependency-bump A 119 tokens
- Skill documentation A 100 tokens
- Skill reflect A 146 tokens
- Skill stacktrace-triage A 112 tokens
- Skill ci-failure-triage A 127 tokens
- Skill duplicate-code-detector A 92 tokens
- Skill mutation-testing A 139 tokens
- Skill postgres A 131 tokens
- Skill research A 108 tokens
- Skill wcag-audit A 110 tokens
- Skill audit-skills A 54 tokens
- Skill bugmagnet A 156 tokens
- Skill fix-loop A 81 tokens
- Skill incremental-refactoring A 75 tokens
- Skill performance-optimization A 97 tokens
- Skill github-actions B 140 tokens
- Skill traefik B 165 tokens
- Skill docker-buildkit B 155 tokens
- Skill bash-hardening B 146 tokens
- Skill rust C 158 tokens
- Skill secrets-management C 145 tokens
- Skill hetzner C 169 tokens
- Agent security-auditor A 120 tokens
- Agent debugger A 90 tokens
- Agent evaluator A 63 tokens
- Agent refactor-scan A 52 tokens
- Agent code-reviewer A 39 tokens
- Agent code-simplifier A 39 tokens
- Agent fixer A 31 tokens
- Hook Stop A not measured
- Hook Notification A not measured
- Hook PostToolUse A not measured
- Hook PreToolUse A not measured
- Hook SubagentStop A not measured
- Hook UserPromptSubmit A not measured
- Hook SessionStart B not measured
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.
- 2mo ago First seen · 20 lines scan A d5f707248f39
ct is a plugin published in the GitHub repository pvillega/claude-templates (23 stars, last pushed 3mo 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 2026-08-30.
ct compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ctpvillega/claude-templates | Plugin | 23 | 3mo ago | none | A | — | Claude Code |
| superpowersobra/superpowers | Plugin | 315k | 6d ago | MIT | A | — | Gemini CLI |
| superpowers-zhjnMetaCode/superpowers-zh | Plugin | 8.5k | 14d ago | MIT | A | — | Gemini CLI |
| aegisGanyuanRan/Aegis | Plugin | 1.4k | 5d ago | MIT | A | — | Claude Code |
| debuggingmelodic-software/claude-code-plugins | Plugin | 30 | today | MIT | A | — | Claude Code |
| knowledge-virtuosokrzysztofsurdy/code-virtuoso | Plugin | 27 | 13d ago | MIT | A | — | Claude Code |
| god-prompt-mcpAKzar1el/god-prompt-mcp | Plugin | 2 | yesterday | MIT | A | — | Gemini CLI |