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/gtapps/claude-code-hermit/docker-setupnpx skills add gtapps/claude-code-hermit --skill docker-setupgit clone --depth 1 https://github.com/gtapps/claude-code-hermitWhat 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 | $0.14454 |
| Opus 5 | $0.00026 | $0.07227 |
| Sonnet 5 | $0.00010 | $0.02891 |
| Haiku 4.5 | $0.00005 | $0.01445 |
Grade B, and why
docker-setup scanned grade B with 2 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.
- **Daemon not running** → `docker info` errors → start Docker Desktop or `sudo systemctl start docker`, then re-run this skill Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
8b. **Public-repo pre-flight (for every non-`claude-plugins-official` entry that the operator has tentatively confirmed in steps 7 or 8).** From the host, run an unauthenticated check against `https://github.com/<org>/<r How it starts
The opening of the file, as written. The whole thing — 599 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker Setup
Generate Docker scaffolding for running hermit as an always-on autonomous agent in a container. Docker provides isolation, crash recovery, and a reproducible environment. The default auto mode (classifier-reviewed autonomy) works well for most Docker hermits. Operators who need zero prompts for fully unattended operation can opt into bypassPermissions via /hermit-settings permissions.
Tone: Friendly guided wizard. Celebrate progress. When something fails, help fix it.
Important: Step 0's container check is a hard short-circuit — run it first and abort on container before anything else. After confirming host execution, run docker-preflight.ts once (Step 1) — it gathers all the read-only signals (docker presence, config existence, WSL path, existing docker files, host ~/.gitconfig, auto-memory seed, a live non-Docker owner of the state dir) as a single JSON blob, so don't fan those probes out into separate Bash calls. Reuse its result for the git-identity (Step 4) and auto-memory (Step 5) decisions rather than re-probing. Step 2's project-dependency scan stays normal file reads (Read tool) plus analysis. Everything that mutates state or drives the container (file backups, docker compose, tmux, mkdir/touch setup-mode, status polls, channel send-keys) must run strictly sequentially in its documented order — never batch those.
Templates live in ${CLAUDE_SKILL_DIR}/../../state-templates/docker/.
Plan
0. Refuse to run inside the hermit container
This skill is host-only — it generates Docker scaffolding on the host filesystem and drives docker compose up.
Run: [ -f /.dockerenv ] || [ -f /run/.containerenv ] && echo container || echo host
If the output is container, stop immediately — do not proceed to step 1. Print:
This skill generates host-side Docker scaffolding and then drives
docker compose up. Run it from your host shell in the project root. To check what's already configured inside the running container, run/claude-code-hermit:hermit-doctor.
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 · 599 lines · 51 tokens per session scan B 443d80ed2bfe
docker-setup is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 14,454 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). 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…