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/nimadorostkar/Claude-Skills-collectionWrote 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/nimadorostkar/claude-skills-collection/agent-tooling)<a href="https://agentmods.dev/plugins/nimadorostkar/claude-skills-collection/agent-tooling"><img src="https://agentmods.dev/badge/plugins/nimadorostkar/claude-skills-collection/agent-tooling/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/nimadorostkar/claude-skills-collection/agent-tooling"><img src="https://agentmods.dev/badge/plugins/nimadorostkar/claude-skills-collection/agent-tooling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-tooling 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": "agent-tooling",
"description": "Agent Tooling — Building the skills, hooks, commands, and plugins that agents run on.",
"source": "./",
"strict": false,
"category": "agent-tooling",
"skills": [
"./skills/agent-tooling/agent-instructions",
"./skills/agent-tooling/agent-memory",
"./skills/agent-tooling/hooks",
"./skills/agent-tooling/plugin-development",
"./skills/agent-tooling/skill-authoring",
"./skills/agent-tooling/skill-review",
"./skills/agent-tooling/slash-commands",
"./skills/agent-tooling/subagents"
]
}What it installs
The manifest is a name and a version. 8 skills travel with it, and installing the plugin installs all of them — 757 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside marketplace.json#agent-tooling 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 · 17 lines scan A 6fdf8a71a009
agent-tooling is a plugin published in the GitHub repository nimadorostkar/Claude-Skills-collection (29 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 2026-10-11.
Other plugins, from other repositories
context-level
Gives Claude a tool that reads how much of the context window remains.
context-degradation
Patterns for recognizing and mitigating context failures in LLM agents. Covers lost-in-middle, context poisoning, distraction, confusion, clash, and model-agnostic degradation measurement.
context-optimization
Techniques for extending effective context capacity through compaction, observation masking, KV-cache optimization, and context partitioning. Double or triple effective context without larger models.
pm-agentops
Operate AI agents and LLM features in production: prompt regression suites, model migration plans, context-engineering reviews, agent incident postmortems, and observability specs — plus the pm-ai evaluation and cost skills they build on.
knowledge-and-memory
Research methodology, corpus search, persistent memory, iterative workflows, and project knowledge management.
casely
Virtual QA lead: turns requirements into TestRail-ready test cases in one conversation, plus a runnable Postman collection when the spec describes an API.