flisk: Skill for Claude Code

.claude/skills/flisk-up/SKILL.md

flisk-up is a skill for Claude Code from flisk-sh/flisk. It costs 85 tokens per session (710 once invoked), scanned A, original, MIT.

A procedure for starting Flisk application stacks from service manifests, which are files describing each service and its settings.

In plain words
What is it for?
Use it to bring up one or more local stacks, start services in dependency order, and confirm their local URLs.
Why use it?
It previews what will start, generates the needed local configuration, and checks service health instead of leaving you to assemble Docker or Tilt files by hand.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is flisk-sh/flisk's own configuration. It tells Claude Code how to work on flisk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything flisk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to flisk-sh/flisk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/flisk-sh/flisk/main/.claude/skills/flisk-up/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/flisk-sh/flisk

Made for: Claude Code.

Wrote 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.

agentmods badge for flisk-up

README.md
[![agentmods](https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-up/github.svg)](https://agentmods.dev/skills/flisk-sh/flisk/flisk-up)
Your own site
<a href="https://agentmods.dev/skills/flisk-sh/flisk/flisk-up"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-up/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.

agentmods 80×15 button for flisk-up

Your own site · 80×15
<a href="https://agentmods.dev/skills/flisk-sh/flisk/flisk-up"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-up.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.00710
Opus 5.5 $0.00034 $0.00284
Sonnet 5.5 $0.00017 $0.00142
Haiku 4.5 $0.00009 $0.00071

Measured 5d ago against content hash cebe1ee948c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

flisk-up 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 5d 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.

.claude/skills/flisk-up/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flisk up

Start local services from service.json manifests. Flisk writes the Docker and Tilt configuration; do not write Dockerfiles, Tiltfiles, or routes by hand.

Workflow

  1. Run flisk doctor if the machine has not been checked yet. Stop on unresolved errors.
  2. Preview the stack: flisk up <stack> --dry-run. Show the user which services and URLs will start.
  3. Start it: flisk up <stack>. Omit <stack> to start every stack.
  4. Confirm health with flisk status --json. Report each service's URL only after it reports healthy.
  5. If flisk up refuses to start because generated files differ from service.json, regenerate from the source manifest. Use --ignore-drift only when the user asks to start anyway.

Services that run without Docker

A service whose service.json declares command (for example "command": "node server.js", with appName, appType, port, dependsOn and an optional healthCheckPath) runs as a local process. When every selected service has one, flisk up needs no Docker and no Tilt: it starts them in dependsOn order, prints http://localhost:<port> for each, prefixes their output, and restarts a service that exits. It stays in the foreground; flisk down stops it from another terminal.

  • Prefer command services for a simple app (an API, a website, a worker). Use Docker services when the app needs a database, one gateway URL, or the container it deploys.
  • A database or cache can run in Docker next to command services: give it an image (no command, no dockerfile) and flisk up starts it with docker run (a mixed run, docs/run-without-docker.md). Any other mix, such as a service built from a Dockerfile next to a command service, is refused with MIXED_RUNTIME.
  • flisk up --json reports "runtime": "native" and each service's URL. Read output with flisk logs --service <name>.
  • Guide: docs/run-without-docker.md.

Guardrails

  • Ask before starting a large stack or one likely to build many images; cold builds can take several minutes.
  • Use flisk up -f only when the user agrees to kill the existing Tilt process.
  • Do not edit .autogenerated/ or other generated output. Change service.json instead.
  • Flisk runs locally. Do not use it to deploy to a cluster.

Read the full file on GitHub · 38 lines

Changes

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.

  1. 5d ago First seen · 38 lines · 85 tokens per session scan A cebe1ee948c6

Subscribe to this mod's changes

flisk-up is a skill published in the GitHub repository flisk-sh/flisk (54 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 710 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-15.

Related

flisk-up compared with skills from other repositories

flisk-up next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
flisk-upflisk-sh/fliskSkill54yesterdayMITA85Claude Code
harborav/harborSkill3.3k9d agoApache-2.0A114Claude Code
docker-local-buildkurtosis-tech/kurtosisSkill559todayApache-2.0A56Claude Code, Codex
k8s-dev-deploykurtosis-tech/kurtosisSkill559todayApache-2.0A78Claude Code, Codex
docker-debugkurtosis-tech/kurtosisSkill559todayApache-2.0A45Claude Code, Codex
k8s-clean-clusterkurtosis-tech/kurtosisSkill559todayApache-2.0A59Claude Code, Codex
k8s-debug-podskurtosis-tech/kurtosisSkill559todayApache-2.0A62Claude Code, Codex