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-agent-ops/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-agent-ops)<a href="https://agentmods.dev/skills/flisk-sh/flisk/flisk-agent-ops"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-agent-ops/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-agent-ops"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-agent-ops.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 | $0.00143 | $0.00795 |
| Opus 5.5 | $0.00057 | $0.00318 |
| Sonnet 5.5 | $0.00029 | $0.00159 |
| Haiku 4.5 | $0.00014 | $0.00080 |
Grade A, and why
flisk-agent-ops 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 4d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flisk Agent Operations Guide
When building, adding, or modifying services in this workspace, do not hand-write Dockerfiles, Docker Compose files, or container manifests. Flisk automatically manages containerization, networking (Traefik), dependencies, and hot reload.
Core Rules for AI Coding Agents
-
Always use Flisk to scaffold new services:
- Scaffold an AI agent:
flisk resource <name> --type agent [--durability files|postgres] - Scaffold an MCP tool server:
flisk resource <name> --type mcp - Scaffold a backend API:
flisk resource <name> --type backend [--framework hono|express|fastify] - Scaffold a worker:
flisk resource <name> --type worker - Scaffold a frontend:
flisk resource <name> --type frontend [--framework react|vue|next] - Wrap an existing Dockerfile or image:
flisk resource <name> --type bring-your-own --dockerfile ./Dockerfile(or--image <name>)
- Scaffold an AI agent:
-
The
agentProcess Contract:/health: Liveness only. Responds 200 when the process is alive./ready: Readiness check. Responds 200 when the checkpoint store (named volume or Postgres) is reachable./turn(POST): Accepts a JSON body{"input": "..."}with headerx-session-id: <session-id>./session(GET): Returns checkpointed messages and turns for the session specified inx-session-id./sessions(GET): Lists the stored sessions, newest first.- Checkpoints persist across container restarts and
flisk down/flisk up.
-
Operate via MCP or CLI:
- Preflight & diagnostics:
flisk doctor --json(or tooldoctor) - Start the stack:
flisk up --json(or toolup) - Inspect status:
flisk status --json(or toolstatus) - Check logs:
flisk logs --tail 200 --json(or toollogs) - Restart a service:
flisk restart <resource> --json(or toolresource_restart); add--rebuild(tool:rebuild: true) when the image or the project.envchanged - List agents:
flisk resources --type agent --json(or toolagent_list) - List agent sessions:
flisk agent sessions <resource> --json(or toolagent_sessionswithresource); add--session-id <id>(tool:sessionId) to read one session's checkpoint - Stop services:
flisk down --json(or tooldown)
- Preflight & diagnostics:
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.
- 4d ago Changed b66daf1fce61
- 5d ago First seen · 42 lines · 143 tokens per session scan A 5d962b09215f
flisk-agent-ops is a skill published in the GitHub repository flisk-sh/flisk (54 stars, last pushed yesterday), licensed MIT. It adds 143 tokens to every session and 795 once invoked, about $0.0006 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-agent-ops compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flisk-agent-opsflisk-sh/flisk | Skill | 54 | yesterday | MIT | A | 143 | Claude Code |
| harborav/harbor | Skill | 3.3k | 9d ago | Apache-2.0 | A | 114 | Claude Code |
| docker-local-buildkurtosis-tech/kurtosis | Skill | 559 | today | Apache-2.0 | A | 56 | Claude Code, Codex |
| k8s-dev-deploykurtosis-tech/kurtosis | Skill | 559 | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| docker-debugkurtosis-tech/kurtosis | Skill | 559 | today | Apache-2.0 | A | 45 | Claude Code, Codex |
| k8s-clean-clusterkurtosis-tech/kurtosis | Skill | 559 | today | Apache-2.0 | A | 59 | Claude Code, Codex |
| k8s-debug-podskurtosis-tech/kurtosis | Skill | 559 | today | Apache-2.0 | A | 62 | Claude Code, Codex |