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/CrashBytes/claude-role-skillsWrote 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/crashbytes/claude-role-skills/claude-role-skills)<a href="https://agentmods.dev/plugins/crashbytes/claude-role-skills/claude-role-skills"><img src="https://agentmods.dev/badge/plugins/crashbytes/claude-role-skills/claude-role-skills/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/crashbytes/claude-role-skills/claude-role-skills"><img src="https://agentmods.dev/badge/plugins/crashbytes/claude-role-skills/claude-role-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
role-based-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 10d 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": "role-based-skills",
"description": "7 role-based professional skills for software teams: Scrum Master, Product Owner, Product Manager, UX/UI Developer, InfoSec Engineer, DevOps Engineer, and Software Migration Engineer. Each skill includes MCP integration support for Jira, Azure DevOps, GitHub, GitLab, Linear, and Trello.",
"version": "1.0.0",
"author": {
"name": "CrashBytes",
"url": "https://crashbytes.ai"
},
"homepage": "https://crashbytes.ai/tutorials/building-claude-code-skills-scrum-master-anthropic-2026",
"repository": "https://github.com/CrashBytes/claude-role-skills",
"license": "Apache-2.0",
"keywords": [
"scrum",
"product-owner",
"product-manager",
"ux-ui",
"infosec",
"devops",
"migration",
"agile",
"skills",
"team-roles"
]
}
What it installs
The manifest is a name and a version. 7 skills, 15 commands travel with it, and installing the plugin installs all of them — 1,011 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill devops-engineer A 150 tokens
- Skill software-migration-engineer A 141 tokens
- Skill infosec-engineer A 138 tokens
- Skill product-manager A 113 tokens
- Skill product-owner A 109 tokens
- Skill scrum-master A 103 tokens
- Skill ux-ui-developer A 117 tokens
- Command accessibility-audit A 16 tokens
- Command deploy-strategy A 13 tokens
- Command retro A 6 tokens
- Command security-review A 8 tokens
- Command backlog-prioritize A 16 tokens
- Command design-system A 7 tokens
- Command legacy-audit A 7 tokens
- Command migrate A 6 tokens
- Command pipeline A 13 tokens
- Command prd A 5 tokens
- Command roadmap A 8 tokens
- Command threat-model A 10 tokens
- Command sprint-plan A 11 tokens
- Command standup A 8 tokens
- Command user-story A 6 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.
- 10d ago First seen · 25 lines scan A 22a778274402
role-based-skills is a plugin published in the GitHub repository CrashBytes/claude-role-skills (6 stars, last pushed 6mo 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 2026-08-31.
Other plugins, from other repositories
pmo
Enterprise program management office: portfolio governance, program and project delivery, dependencies and delivery risk, benefits realization, and adoption.
operations
Program management, process design, vendor and supplier management, and operational delivery.
people
Org design, hiring and interviewing, compensation and leveling, and workforce planning.
revenue
Outbound, sales enablement, revenue operations, pricing and packaging, activation, retention, and referrals.
gh
File durable GitHub issues with reproductions, pinned links, and stripped PII. Enforces a markdown writing discipline reusable for any PR, comment, or ticket.
situate
Gain situational awareness before modifying code. Scans branches, PRs, tickets, and project conventions to orient the agent and verify the work required.