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.
curl -O https://raw.githubusercontent.com/flisk-sh/flisk/main/.claude/skills/flisk-doctor/SKILL.mdgit clone --depth 1 https://github.com/flisk-sh/fliskWrote 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/skills/flisk-sh/flisk/flisk-doctor)<a href="https://agentmods.dev/skills/flisk-sh/flisk/flisk-doctor"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-doctor/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/skills/flisk-sh/flisk/flisk-doctor"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00094 | $0.00752 |
| Opus 5.5 | $0.00038 | $0.00301 |
| Sonnet 5.5 | $0.00019 | $0.00150 |
| Haiku 4.5 | $0.00009 | $0.00075 |
Grade A, and why
flisk-doctor 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flisk doctor
Use the CLI's environment and project checks as the starting point for Flisk setup and diagnosis.
Workflow
- Run
flisk doctorfrom the Flisk project root. - Read the full output and distinguish host prerequisites from project configuration findings.
- Fix the source configuration or environment item named by the diagnostic. Do not hand-edit generated
.autogenerated/output. - Run
flisk doctoragain to confirm the finding is resolved. - Before starting services, use
flisk networksto inspect the routed URLs; start only the needed stack withflisk up <stack>when appropriate.
When the standard check is not enough
flisk doctor has no --verbose flag of its own. Use these instead:
flisk doctor --allruns every check and prints the Machine and Project sections with a summary.flisk doctor --jsonprints the versioned readiness report: each check's name, result, message and fix. Read it instead of parsing the human output.flisk doctor --no-pingskips pinging the/healthof running services;--ping-timeout <ms>gives slow services longer.flisk doctor --strictfails on warnings too, such as a WSL project under/mnt/c.flisk config verify --jsonchecks that the generated files match.flisk/project.jsonand everyservice.json. Doctor checks the machine and the services;config verifychecks generated-file consistency.FLISK_VERBOSE=1prints error details that some commands (for exampleflisk networksandflisk upgrade) otherwise hide.FLISK_DEBUG=1 flisk up --verboseadds the engine's Starlark debug logs to the Tilt output.
Repairs
flisk doctor --fix --dry-runlists the repairs without changing anything.flisk doctor --fixapplies them after asking (--yesskips the question). It removes this project's unused Docker networks and leftover doctor probes.- When Docker refuses new networks (
all predefined address pools have been fully subnetted), runflisk doctor --fix --scope=machine. It also removes the unused networks of other Flisk projects, and skips any network a container is attached to.
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.
- 5d ago First seen · 47 lines · 94 tokens per session scan A d444e8711226
flisk-doctor is a skill published in the GitHub repository flisk-sh/flisk (54 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 752 once invoked, about $0.0004 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.
flisk-doctor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flisk-doctorflisk-sh/flisk | Skill | 54 | yesterday | MIT | A | 94 | Claude Code |
| docker-debugkurtosis-tech/kurtosis | Skill | 559 | today | Apache-2.0 | A | 45 | Claude Code, Codex |
| k8s-debug-podskurtosis-tech/kurtosis | Skill | 559 | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| docker-docspledgeandgrow/pledge-skills | Skill | 11 | 4mo ago | MIT | A | 93 | Claude Code, Codex |
| docker-managementfurkangonel/cowrangler | Skill | 1 | 2mo ago | MIT | C | 16 | Claude Code, Codex |
| gke-kueue-troubleshootinggoogle/skills | Skill | 24k | today | Apache-2.0 | A | 253 | Claude Code, Codex |
| smoke-testgarrytan/gbrain | Skill | 33k | today | MIT | A | 79 | Claude Code |