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 kossakovsky/cc-pluginsnpx agentmods add plugins/kossakovsky/cc-plugins/marketplacegit clone --depth 1 https://github.com/kossakovsky/cc-pluginsGrade A, and why
cc-plugins 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 yesterday.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "cc-plugins",
"owner": {
"name": "kossakovsky"
},
"metadata": {
"description": "Community marketplace of plugins for Claude Code",
"version": "1.0.0"
},
"plugins": [
{
"name": "switch-provider",
"description": "Switch Claude Code between AI providers (Anthropic, Z.AI, Kimi, MiniMax) with a single command",
"version": "1.0.0",
"author": {
"name": "kossakovsky"
},
"source": "./plugins/switch-provider",
"category": "ai-tools",
"tags": ["provider", "api", "configuration"],
"keywords": ["provider", "switch", "api", "zai", "kimi", "minimax"]
},
{
"name": "plugin-development",
"description": "A comprehensive toolkit for creating, validating, and distributing Claude Code plugins",
"version": "1.3.0",
"author": {
"name": "kossakovsky"
},
"source": "./plugins/plugin-development",
"category": "developer-tools",
"tags": ["development", "plugins", "scaffold", "validation", "tools"],
"keywords": ["claude-code", "plugins", "developer-tools", "plugin-development", "plugin-authoring", "scaffold", "scaffolding", "validation"]
},
{
"name": "commit",
"description": "Smart git commits with conventional commit message generation",
"version": "1.0.0",
"author": {
"name": "kossakovsky"
},
"source": "./plugins/commit",
"category": "developer-tools",
"tags": ["git", "commits", "conventional-commits"],
"keywords": ["git", "commit", "conventional-commits", "changelog"]
},
{
"name": "writing-skills",
"description": "Create, test, and bulletproof Claude Code skills using TDD methodology. Based on obra/superpowers writing-skills",
"version": "1.0.0",
"author": {
"name": "obra"
},
"source": "./plugins/writing-skills",
"category": "developer-tools",
"tags": ["skills", "tdd", "testing", "development"]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.
- yesterday First seen · 61 lines scan A 67c0e31b652e
cc-plugins is a plugin published in the GitHub repository kossakovsky/cc-plugins (3 stars, last pushed 5mo 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 2026-08-31.
Other plugins, from other repositories
skarn-guard
Real-time guard on five Claude Code pre-execution hook events (tool calls, permission decisions, submitted and expanded prompts, and subagent creation) plus a response-end advisory that flags an action leaking a secret, installing a malicious package, or exfiltrating data, plus the skarn-audit skill (scan sessions and.
goalkeeper
Durable goal-following for Claude Code: contracts with definition-of-done, subagent judge gates, and linear chains.
noisy-tools-in-subagent
Forces noisy commands (builds, tests, linters, static analysis) to run inside a Sonnet subagent instead of the main context, preserving main-agent tokens.
forge
A generator: it interviews an organization and emits a standalone, org-owned Claude Code plugin (the org's agent harness) aligned to how that org actually works. Karpathy-schema wiki + role/subagent pattern + skill verbs + tool adapters + the operating model. Re-emit to upgrade; never fork.
coaltipple
CoalTipple — model/effort router for Claude Code. Delegates a task you CAN do but is large+cheap DOWN to a lower tier to save tokens; escalates a task beyond the current tier UP for quality — up to Fable 5, the top rung (a consent-gated, real-money spawn). Two-knob routing (tier × effort, effort-before-tier), an alias.
zAI-Skills
Development marketplace for AI-Toolkit, consulting-toolkit, real-estate-investment, career-coach, and plugin-forge plugins.