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 rohitg00/awesome-claude-code-toolkitnpx agentmods add plugins/rohitg00/awesome-claude-code-toolkit/awesome-claude-code-toolkitgit clone --depth 1 https://github.com/rohitg00/awesome-claude-code-toolkitGrade A, and why
awesome-claude-code-toolkit 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.
What it actually says
{
"name": "claude-code-toolkit",
"version": "1.0.0",
"description": "Complete developer toolkit for Claude Code",
"author": "Rohit Ghumare",
"license": "Apache-2.0"
}
What it installs
The manifest is a name and a version. 25 hooks, 20 plugins travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.
- Hook 0 A not measured
- Hook 1 A not measured
- Hook 10 A not measured
- Hook 11 A not measured
- Hook 12 A not measured
- Hook 13 A not measured
- Hook 14 A not measured
- Hook 15 A not measured
- Hook 16 A not measured
- Hook 17 A not measured
- Hook 18 A not measured
- Hook 19 A not measured
- Hook 2 A not measured
- Hook 20 A not measured
- Hook 21 A not measured
- Hook 22 A not measured
- Hook 23 A not measured
- Hook 24 A not measured
- Hook 3 A not measured
- Hook 4 A not measured
- Hook 5 A not measured
- Hook 6 A not measured
- Hook 7 A not measured
- Hook 8 A not measured
- Hook 9 A not measured
- Plugin accessibility-checker 2 inside A not measured
- Plugin api-architect 3 inside A not measured
- Plugin a11y-audit 2 inside A not measured
- Plugin adr-writer 2 inside A not measured
- Plugin ai-prompt-lab 2 inside A not measured
- Plugin analytics-reporter 2 inside A not measured
- Plugin android-developer 2 inside A not measured
- Plugin api-benchmarker 1 inside A not measured
- Plugin api-reference 1 inside A not measured
- Plugin api-tester 2 inside A not measured
- Plugin aws-helper 2 inside A not measured
- Plugin azure-helper 2 inside A not measured
- Plugin backend-architect 2 inside A not measured
- Plugin bug-detective 2 inside A not measured
- Plugin bundle-analyzer 2 inside A not measured
- Plugin changelog-gen 1 inside A not measured
- Plugin changelog-writer 1 inside A not measured
- Plugin ci-debugger 2 inside A not measured
- Plugin code-architect 2 inside A not measured
- Plugin code-explainer 2 inside 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.
- 3d ago First seen · 8 lines scan A fe40a01892d6
awesome-claude-code-toolkit is a plugin published in the GitHub repository rohitg00/awesome-claude-code-toolkit (2,578 stars, last pushed 3mo ago), licensed Apache-2.0. 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
taches-cc-resources
Curated Claude Code skills and commands for prompt engineering, MCP servers, subagents, hooks, and productivity workflows.
insurgent-campaign
Produces grassroots-first campaign plans for startups, NGOs, movements, and solo brands being outspent by incumbents. Ideates campaigns of any kind (awareness, launch, fundraising, mobilization, counter-narrative), audits spend asymmetry, assembles an insurgent channel stack with 70/30 boost rules, and outputs a…
adaptive-communication
Detects user communication style (high-context relational vs low-context transactional) and adapts responses accordingly.
bencium-aeo
Answer Engine Optimization for AI search visibility. Optimize content for ChatGPT, Claude, Gemini, AI Overviews citations.
emotion-statusline
Statusline that shows Claude's classified emotional state (behavioral, Haiku-scored) with a reward-hacking warning on 'desperate'.
hungarian-humanizer
Detect and remove AI-generated markers from Hungarian text so it reads like a native speaker wrote it. 26 patterns (12 Hungarian-specific + 14 universal) plus 4 style markers.