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.
npx agentmods add skills/cskwork/fizzy-skill/fizzynpx skills add cskwork/fizzy-skill --skill fizzygit clone --depth 1 https://github.com/cskwork/fizzy-skillWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.02939 |
| Opus 5 | $0.00022 | $0.01470 |
| Sonnet 5 | $0.00009 | $0.00588 |
| Haiku 4.5 | $0.00004 | $0.00294 |
Grade B, and why
fizzy scanned grade B with 3 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
2. Save to `~/.config/fizzy/.env` (chmod 600): Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> `fizzy-cli auth login --email --code` is broken in non-TTY — each call re-issues a code, invalidating any pasted one. Workaround: see `references/magic-link-curl-two-step.md`. Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Bash heredoc + `(` / backtick | `unexpected EOF` or `command not found` | Build bodies in Python with `subprocess.run([cmd, '--description', text])` | How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fizzy
Operate tobiasbischoff/fizzy-cli against a self-hosted Fizzy instance. Single skill covers:
- Onboarding — install, base-URL, auth (PAT or magic-link), default account
- Daily ops — board/card/comment CRUD with the rendering gotchas baked in
- Jira → Fizzy migration — pull a Jira issue's description, attachments, and comment thread into a card (+ sub-cards) without losing formatting
Quick decision
Need to set up fizzy-cli from scratch? → §1 Onboarding
Need to create/update cards or comments? → §2 Daily ops
Need to import a Jira issue into Fizzy? → §3 Jira → Fizzy migration
Markdown looks broken after posting to Fizzy? → §4 Rendering
Inputs (env)
FIZZY_HOST— base URL (e.g.https://fizzy.example.com)FIZZY_EMAIL— account emailFIZZY_TOKEN(preferred) OR magic-link from inbox
For Jira import: acli must be authenticated to the source site (acli auth status → ✓).
§1 Onboarding
1.1 Install
Homebrew (documented):
brew install tobiasbischoff/tap/fizzy-cli
If brew is blocked, build from source:
git clone https://github.com/tobiasbischoff/fizzy-cli.git ~/.local/src/fizzy-cli
cd ~/.local/src/fizzy-cli && go build -o ~/.local/bin/fizzy-cli ./cmd/fizzy-cli
Pitfall —
go installdoes NOT work.go.moddeclaresmodule fizzy-cli(short form), sogo install github.com/...fails. Always clone +go build -o.
1.2 Point at the host
fizzy-cli config set --base-url "$FIZZY_HOST"
fizzy-cli config show
Config: macOS ~/Library/Application Support/fizzy/config.json, Linux ~/.config/fizzy/config.json.
1.3 Authenticate
A. PAT (preferred, idempotent):
fizzy-cli auth login --token "$FIZZY_TOKEN"
fizzy-cli auth status # → "Authenticated using token."
B. Magic-link in non-TTY (Claude Code / CI):
fizzy-cli auth login --email --codeis broken in non-TTY — each call re-issues a code, invalidating any pasted one. Workaround: seereferences/magic-link-curl-two-step.md.
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 · 239 lines · 44 tokens per session scan B aa7b227a6a11
fizzy is a skill published in the GitHub repository cskwork/fizzy-skill (1 stars, last pushed 11d ago), licensed MIT. It adds 44 tokens to every session and 2,939 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
kanban-orchestrator
Kanban orchestrator: decompose, route, verify. No executing.
kanban-worker
Kanban worker lifecycle: claim, work, heartbeat, complete.
agentflow
AgentFlow workflow skill. Use this skill when the user needs Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution…
project-management
Agile methodologies, issue tracking, and team collaboration tools.
pm-config
Initialize or reconfigure MDPM (ID prefix, task directories, sync preferences).
pm-sync-jira
Sync task state with Jira via MCP (optional, graceful degradation).