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 CrumbtrailDev/crumbtrail-clinpx agentmods add plugins/crumbtraildev/crumbtrail-cli/crumbtrail-skillsgit clone --depth 1 https://github.com/CrumbtrailDev/crumbtrail-cliWrote 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/crumbtraildev/crumbtrail-cli/crumbtrail-skills)<a href="https://agentmods.dev/plugins/crumbtraildev/crumbtrail-cli/crumbtrail-skills"><img src="https://agentmods.dev/badge/plugins/crumbtraildev/crumbtrail-cli/crumbtrail-skills.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
crumbtrail-skills 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 4d 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "crumbtrail-skills",
"description": "Failure archetype skills for Crumbtrail. Each skill pairs one recurring failure shape with the exact Crumbtrail MCP calls that confirm or rule it out, so an agent troubleshoots against a recorded session instead of a generic checklist.",
"version": "0.1.0",
"author": { "name": "Crumbtrail", "url": "https://github.com/CrumbtrailDev" },
"homepage": "https://crumbtrail.ai",
"repository": "https://github.com/CrumbtrailDev/crumbtrail-cli",
"license": "MIT",
"keywords": [
"debugging",
"skills",
"failure-archetypes",
"troubleshooting",
"bug-context"
]
}
What it installs
The manifest is a name and a version. 13 skills travel with it, and installing the plugin installs all of them — 809 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill async-lifecycle-race A 0 tokens
- Skill env-promotion A 94 tokens
- Skill format-boundary A 0 tokens
- Skill lying-status A 0 tokens
- Skill missing-key-detonation A 84 tokens
- Skill new-path-parity A 99 tokens
- Skill stale-derived-state A 85 tokens
- Skill dependency-bump A 79 tokens
- Skill flag-landmine A 71 tokens
- Skill orphan-cascade A 71 tokens
- Skill reference A 61 tokens
- Skill scale-cliff A 84 tokens
- Skill unowned-contract A 81 tokens
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.
- 4d ago First seen · 18 lines scan A f6b455cced7a
crumbtrail-skills is a plugin published in the GitHub repository CrumbtrailDev/crumbtrail-cli (0 stars, last pushed today), 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
kernel-sdks
TypeScript and Python SDK skills for building browser automation with Kernel's Typescript and Python SDKs.
realbrowser
Target-first local Chrome/Chromium browser control with signed-in profiles, labeled tabs, and guarded actions.
headless
Headless browser automation for site comparison, E2E testing, and anti-bot-aware web research.
claudeshot
Lightweight screenshot capture for Claude Code. PREFERRED over Playwright for web screenshots - uses headless Chrome directly without MCP overhead. Use /screenshot --web URL for quick page captures instead of Playwright browser tools.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.