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.
/plugin marketplace add davila7/claude-code-templatesnpx agentmods add plugins/davila7/claude-code-templates/marketplacegit clone --depth 1 https://github.com/davila7/claude-code-templatesGrade A, and why
claude-code-templates marketplace 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 3d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"agents": [
{
"name": "frontend-developer",
"version": "1.0.0",
"author": {
"name": "Claude Code Templates Team"
},
"category": "development",
"keywords": ["frontend", "react", "typescript", "ui", "responsive", "accessibility"],
"license": "MIT",
"repository": "https://github.com/davila7/claude-code-templates"
},
{
"name": "backend-architect",
"version": "1.0.0",
"author": {
"name": "Claude Code Templates Team"
},
"category": "development",
"keywords": ["backend", "api", "microservices", "database", "architecture", "scalability"],
"license": "MIT",
"repository": "https://github.com/davila7/claude-code-templates"
},
{
"name": "fullstack-developer",
"version": "1.0.0",
"author": {
"name": "Claude Code Templates Team"
},
"category": "development",
"keywords": ["fullstack", "frontend", "backend", "database", "api", "typescript"],
"license": "MIT",
"repository": "https://github.com/davila7/claude-code-templates"
},
{
"name": "devops-engineer",
"version": "1.0.0",
"author": {
"name": "Claude Code Templates Team"
},
"category": "devops",
"keywords": ["devops", "ci-cd", "infrastructure", "kubernetes", "docker", "terraform"],
"license": "MIT",
"repository": "https://github.com/davila7/claude-code-templates"
},
{
"name": "mobile-developer",
"version": "1.0.0",
"author": {
"name": "Claude Code Templates Team"
},
"category": "mobile",
"keywords": ["mobile", "react-native", "flutter", "ios", "android", "cross-platform"],
"license": "MIT",
"repository": "https://github.com/davila7/claude-code-templates"
},
{
"name": "ios-developer",
"version": "1.0.0",
"author": {
"name": "Claude Code Templates Team"
},
"category": "mobiWhat 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.
- 3d ago First seen · 93 lines scan A 5634592867d9
claude-code-templates marketplace is a plugin published in the GitHub repository davila7/claude-code-templates (30,476 stars, last pushed 2d ago), 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 2026-08-30.
Other plugins, from other repositories
italiano-scrittura-anti-ai
Suite per la lingua italiana e sistema avanzato anti AI. Scrive secondo la norma, rivede testi già scritti, traduce senza calchi, misura la voce di un autore su un corpus e difende un testo umano segnalato da un rilevatore automatico.
arch
Architecture and build orchestration agents for system design, multi-agent coordination, and context management.
autocode
You say it, AutoCode ships it. 48 skills. Code to deployment in one session, with I-Lang v5.0 judgment: AI decides the small stuff, checks with you on the costly stuff.
commander-hub marketplace
Plugin marketplace listing 1 plugin: commander.
dotclaude
Code review, pre-flight, worktree isolation, guard hooks, and risk-weighted test coverage for Claude Code. Consumed as-is; /dotclaude:coding and /dotclaude:testing elicit your project's bar.
dotclaude-design
A design/UX audit layer for Claude Code. /dotclaude:design elicits your design north-star; ux, flow, pages, a11y, interaction, and design-token audits grade every screen against it, plus a product-designer IA/flow spec.