Claude Code Templates is a command-line tool and catalogue for configuring Anthropic’s Claude Code with agents, commands, settings, hooks, integrations, skills, and project templates. Developers use it to browse and install reusable components for their coding workflows. The catalogue includes many of these Claude Code components.
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/davila7/claude-code-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/davila7/claude-code-templates/policy-ceiling)<a href="https://agentmods.dev/plugins/davila7/claude-code-templates/policy-ceiling"><img src="https://agentmods.dev/badge/plugins/davila7/claude-code-templates/policy-ceiling/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/davila7/claude-code-templates/policy-ceiling"><img src="https://agentmods.dev/badge/plugins/davila7/claude-code-templates/policy-ceiling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
policy-ceiling 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 2d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "policy-ceiling",
"version": "0.1.0",
"description": "Makes an organization's managed limits act as ceilings and floors over each person's merged settings (retention, model, effort, permission mode, sandbox) instead of fixed values, and shows in /policy the requested value, limit and effective value for each rule.",
"author": {
"name": "claude-code-templates",
"url": "https://www.aitmpl.com"
},
"repository": "https://github.com/davila7/claude-code-templates",
"license": "MIT",
"keywords": [
"mod",
"function-hooks",
"enterprise",
"managed-settings",
"policy"
],
"types": "./types/index.d.ts",
"userConfig": {
"maxCleanupPeriodDays": {
"type": "number",
"title": "Max transcript retention (days)",
"description": "Ceiling for cleanupPeriodDays. 0 means no ceiling. Read from managed settings only.",
"default": 0
},
"deniedModels": {
"type": "string",
"title": "Denied models",
"description": "Comma-separated model names or aliases replaced in the settings `model` (e.g. opus[1m]), and cleared from env ANTHROPIC_MODEL, ANTHROPIC_DEFAULT_OPUS_MODEL, ANTHROPIC_DEFAULT_SONNET_MODEL, ANTHROPIC_DEFAULT_HAIKU_MODEL, ANTHROPIC_SMALL_FAST_MODEL and CLAUDE_CODE_SUBAGENT_MODEL. Not an allowlist: --model and /model are not capped. Read from managed settings only.",
"default": ""
},
"fallbackModel": {
"type": "string",
"title": "Fallback model",
"description": "Model used when the requested one is denied. Empty means Claude Code's default. Read from managed settings only.",
"default": ""
},
"maxEffort": {
"type": "string",
"title": "Max effort",
"description": "Ceiling for effortLevel (top-level and per model): low, medium, high, xhigh or max. Empty means no ceiling. Read from managed settings only.",
"default": ""
},
"forbiddenModes": {
"type": "string",
"title": "Forbidden permission mWhat 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.
- 2d ago First seen · 58 lines scan A 435af6dfd9d2
policy-ceiling is a plugin published in the GitHub repository davila7/claude-code-templates (33,152 stars, last pushed yesterday), licensed MIT. 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 2026-11-04.
policy-ceiling compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| policy-ceilingdavila7/claude-code-templates | Plugin | 33k | yesterday | MIT | A | — | Claude Code |
| databasesandisab/swe-marketplace | Plugin | 21 | yesterday | MIT | A | — | Claude Code |
| dataandisab/swe-marketplace | Plugin | 21 | yesterday | MIT | A | — | Claude Code |
| frontendandisab/swe-marketplace | Plugin | 21 | yesterday | MIT | A | — | Claude Code |
| product-managementandisab/swe-marketplace | Plugin | 21 | yesterday | MIT | A | — | Claude Code |
| commander-hub marketplaceKevinZai/commander | Plugin | 6 | yesterday | MIT | A | — | Claude Code |
| commanderKevinZai/commander | Plugin | 6 | yesterday | MIT | A | — | Claude Code |