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 cskwork/fizzy-skillnpx agentmods add plugins/cskwork/fizzy-skill/fizzy-skillgit clone --depth 1 https://github.com/cskwork/fizzy-skillGrade A, and why
fizzy 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
{
"name": "fizzy",
"version": "0.1.0",
"description": "Operate a self-hosted Fizzy kanban board via fizzy-cli. Use when creating cards or migrating Jira issues to Fizzy.",
"author": {
"name": "cskwork",
"url": "https://github.com/cskwork"
}
}
What ships with it
1 file beside plugin.json 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.
- yesterday First seen · 10 lines scan A 872a41584c48
fizzy is a plugin published in the GitHub repository cskwork/fizzy-skill (1 stars, last pushed 11d 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 2026-08-31.
Other plugins, from other repositories
jira-assistant-skills
Plugin marketplace listing 1 plugin: jira-assistant-skills.
mdpm
Plugin marketplace listing 1 plugin: mdpm.
mdpm
Markdown Project Manager — a lightweight, markdown-native project tracking system for Claude Code. Tasks live as .md files with YAML frontmatter; status is a directory. Optional Jira/Wrike sync via MCP.
reviewable-html-workbench-local
Plugin marketplace listing 1 plugin: reviewable-html-workbench.
dev-day
The complete developer day-loop for Claude Code + Jira: /start-session boots a senior-collaborator session (feedback memory, Jira backlog, standing plan-gate), /standup answers 'anything pending?', /bug-triage root-causes tickets, /groom preps them for estimation, /create-ticket files them, /jira-comment posts clean…
kelvia
The Kelvia plugin for Claude Code: a task board your agent runs, and you can audit.