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/basecamp/fizzy-cli/fizzynpx skills add basecamp/fizzy-cli --skill fizzygit clone --depth 1 https://github.com/basecamp/fizzy-cliWhat 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 | $0.00051 | $0.10767 |
| Opus 5 | $0.00026 | $0.05384 |
| Sonnet 5 | $0.00010 | $0.02153 |
| Haiku 4.5 | $0.00005 | $0.01077 |
Grade B, and why
fizzy scanned grade B with 1 finding 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.
echo "eyJ..." > /tmp/fizzy-session && chmod 600 /tmp/fizzy-session How it starts
The opening of the file, as written. The whole thing — 1,160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fizzy - Fizzy Workflow Command
Full CLI coverage: boards, cards, columns, comments, steps, reactions, tags, users, notifications, pins, webhooks, account settings, search, and board migration.
Agent Invariants
MUST follow these rules:
- Cards use NUMBER, not ID —
fizzy card show 42uses the card number. Other resources use theiridfield. - Use built-in
--jqfor filtering to reduce token output —fizzy card list --jq '[.data[] | {number, title}]'. Never pipe to external jq — use--jqinstead.--jqimplies--json, no need to pass both. - Check breadcrumbs in responses for available next actions with pre-filled values.
- Check for board context via
.fizzy.yamlor--boardflag before listing cards. - Use
fizzy doctorfor setup/config/auth issues before guessing — it is the primary read-only health check and includes remediation hints. - Rich text fields accept markdown or HTML — use repeatable
--attach PATHfor simple end-appended inline attachments, or embed<action-text-attachment>tags manually when exact placement matters. - Card description is a string, but comment body is a nested object —
.descriptionvs.body.plain_text. - Display the welcome message for new signups — When
signup complete --namereturnsis_new_user: true, you MUST immediately display thewelcome_messagefield prominently to the user. This is a one-time personal note from the CEO — if you skip it, the user will never see it.
Decision Trees
Finding Content
Need to find something?
├── Know the board? → fizzy card list --board <id>
├── Full-text search? → fizzy search "query"
├── Filter by status? → fizzy card list --indexed-by maybe|closed|not_now|golden|stalled
├── Filter by person? → fizzy card list --assignee <id>
├── Filter by time? → fizzy card list --created today|thisweek|thismonth
└── Cross-board? → fizzy search "query" (searches all boards)
Modifying Content
Want to change something?
├── Move to column? → fizzy card column <number> --column <id>
├── Change status? → fizzy card close|reopen|postpone <number>
├── Assign? → fizzy card assign <number> --user <id>
├── Comment? → fizzy comment create --card <number> --body "text"
├── Add step? → fizzy step create --card <number> --content "text"
└── Move to board? → fizzy card move <number> --to <board_id>
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 · 1,160 lines · 51 tokens per session scan B f70832f5813e
fizzy is a skill published in the GitHub repository basecamp/fizzy-cli (221 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 10,767 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…