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 2ykwang/agent-skillsnpx agentmods add plugins/2ykwang/agent-skills/instruction-evalgit clone --depth 1 https://github.com/2ykwang/agent-skillsGrade A, and why
instruction-eval 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 2d 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": "instruction-eval",
"version": "0.5.1",
"description": "Change one condition an agent runs under (instruction text, the reference material instructions point at, MCP tools and permissions, hooks, skill files), then run the same prompts before and after, several times each, to see what actually changes. Produces an HTML report showing both arms' answers side by side. Use when deciding whether to add a rule, when you need evidence that an existing rule can be deleted, when picking between two wordings of the same rule, or when checking whether material you placed is actually being read. Triggers on 'does this rule do anything', 'compare before and after adding this', 'can I drop this', 'difference with and without this', 'run an A/B'. Not for application code changes or anything automated tests already verify. Built on Claude Code: it spawns `claude -p` subprocesses to run both arms.",
"author": {
"name": "2ykwang",
"url": "https://github.com/2ykwang"
},
"repository": "https://github.com/2ykwang/agent-skills",
"homepage": "https://github.com/2ykwang/agent-skills/tree/main/skills/instruction-eval",
"license": "MIT"
}
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.
- 2d ago First seen · 13 lines scan A 72e9acd7a547
instruction-eval is a plugin published in the GitHub repository 2ykwang/agent-skills (18 stars, last pushed 29d 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
skill-teilen
Teilt deinen Skill oder dein Plugin automatisch mit der SKAILE Community Skill-Library. Claude übernimmt Fork, Einreichung und Pull Request für dich.
team-up marketplace
Plugin marketplace listing 1 plugin: team-up.
dev-team
Multi-agent development team orchestration with planning and execution pipelines.
meta-prompts
Skills for creating, reviewing, and rewriting agent prompts — including agent/plugin file authoring, SKILL.md design, and PROSE methodology guidance.
plugin-creator
Create and maintain GitHub Copilot CLI and Claude Code plugins and marketplaces, including plugin.json and marketplace.json manifests for both platforms.
skill-guide
Design, write, review, and improve SKILL.md files using proven patterns (Tool Wrapper, Generator, Reviewer, Inversion, Pipeline) with intent-based protocols for creating, reviewing, and improving agent skills.