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 softspark/ai-toolkitnpx agentmods add plugins/softspark/ai-toolkit/appgit clone --depth 1 https://github.com/softspark/ai-toolkitGrade A, and why
app 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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "ai-toolkit",
"displayName": "AI Toolkit",
"description": "Professional-grade engineering skills, agents, rules, and lifecycle guardrails for Claude Code, Claude Chat, and Cowork.",
"version": "4.29.2",
"author": {
"name": "SoftSpark",
"url": "https://github.com/softspark"
},
"repository": "https://github.com/softspark/ai-toolkit",
"license": "Apache-2.0",
"homepage": "https://github.com/softspark/ai-toolkit",
"skills": "./claude-app/skills/",
"hooks": "./claude-app/hooks/hooks.json",
"keywords": [
"development",
"testing",
"deployment",
"security",
"architecture",
"multi-agent",
"orchestration",
"devops",
"code-review",
"ai-toolkit",
"constitution",
"quality-gates",
"skills",
"agents",
"cursor",
"codex",
"opencode",
"cowork",
"claude-app"
]
}
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 · 38 lines scan A 7cedba1e74e4
app is a plugin published in the GitHub repository softspark/ai-toolkit (167 stars, last pushed 3d 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
sap-skills
SAP development skills with evidence-tracked public-source and package-registry verification.
ainb-hooks
Emit every safely observable Claude Code lifecycle event into Hangar's durable provider log. User-facing events still reach ainb-notifyd over its Unix socket. The same notify.sh powers ATC structured control when installed with AINBMANAGED=atc. stallguard.py additionally blocks turn-end when a session would idle on i.
sap-btp-business-application-studio
This skill provides comprehensive guidance for SAP Business Application Studio (BAS), the cloud-based IDE on SAP BTP built on Code-OSS. Use when setting up BAS subscriptions, creating dev spaces, connecting to external systems, deploying MTA applications, troubleshooting connectivity issues, managing Git repositories.
sap-abap
Comprehensive ABAP development skill for SAP systems. Use when writing ABAP code, working with internal tables, structures, ABAP SQL, object-oriented programming, RAP (RESTful Application Programming Model), CDS views, EML statements, ABAP Cloud development, string processing, dynamic programming, RTTI/RTTC, field…
stablecoin-depeg-monitor
Stablecoin peg stability monitoring and historical depeg database. Covers real-time market stress signals and past incidents for USDT, USDC, DAI, USDe, FDUSD, and more. Also peg/reserve risk monitoring for treasuries and custodians.
claude-superskills
Plugin marketplace listing 1 plugin: claude-superskills.