Agent skill

Tsk Config

by dtormoen in dtormoen/tsk-tsk

A skill your agent uses when the user wants to set up or configure tsk Docker container images, customize their tsk.toml for Docker builds, configure stack/agent/project layers, or troubleshoot tsk…

MITAuto-check: notesDevOps & Cloud

Install Tsk Config

skills CLI
$ npx skills add dtormoen/tsk-tsk --skill tsk-config -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dtormoen/tsk-tsk tsk-config --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/dtormoen/tsk-tsk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tsk-config/skills/tsk-config .claude/skills/tsk-config && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
tsk-config
GitHub stars
171
Token cost
~2.8k tokens
SKILL.md length
1,031 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user wants to set up or configure tsk Docker container images, customize their tsk.toml for Docker builds, configure stack/agent/project layers, or troubleshoot tsk…

  • Works in 6 steps: Gather Project Information → Check for Deprecated Dockerfiles → Choose Configuration Location → …
  • The user wants to set up
  • SKILL.md covers Step 1: Gather Project…, Step 2: Check for Deprecated…, Step 3: Choose Configuration… and Step 4: View the Current…, plus 2 more sections
  • Calls apt-get and gh; reaches github.com

What it does

Tsk Config is an agent skill from dtormoen/tsk-tsk. Use this skill when the user wants to set up or configure tsk Docker container images, customize their tsk.toml for Docker builds, configure stack/agent/project layers, or troubleshoot tsk container build issues.

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Containers. It works with Docker and Rust. The repository describes itself as: Keeping your agents out of trouble with sandboxed coding agent automation. The licence is MIT.

When your agent uses it

  • The user wants to set up
  • Configure tsk Docker container images
  • Customize their tsk.toml for Docker builds
  • Configure stack/agent/project layers

Example prompts

  • “/tsk-config”

Requirements

  • Python 3
  • Node.js
  • Docker
  • Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Gather Project Information
  2. Check for Deprecated Dockerfiles
  3. Choose Configuration Location
  4. View the Current Docker Build
  5. Populate Configuration
  6. Test the Configuration

What it can do on your machine

Read from SKILL.md and the folder at commit bc0c0c6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write
    • Edit
    • Glob
    • Grep
    • AskUserQuestion

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • apt-get
    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tsk Config loads about 2.8k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 1,031 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteRuns commands with sudoSKILL.md:313
    # Enable passwordless sudo inside containers
  • NoteRuns commands with sudoSKILL.md:314
    sudo = false
  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from dtormoen/tsk-tsk at commit bc0c0c6, republished under its MIT licence (© dtormoen). 1,031 words, ~2,801 tokens.

Download SKILL.mdSave it as .claude/skills/tsk-config/SKILL.md (or your agent's skills folder).
name
tsk-config
description
Use this skill when the user wants to set up or configure tsk Docker container images, customize their tsk.toml for Docker builds, configure stack/agent/project layers, or troubleshoot tsk container build issues.
allowed-tools
Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion
user-invocable
true
disable-model-invocation
true

tsk Docker Configuration Guide

You are helping a user configure tsk Docker container images for their project. Follow these steps in order.

Step 1: Gather Project Information

Detect the project's technology stack by checking for these files in the project root. These are tsk's built-in stacks with auto-detection — custom stacks for any language can be defined via stack_config in tsk.toml (covered in Step 5).

FileStack
Cargo.tomlrust
go.modgo
package.jsonnode
pyproject.toml, requirements.txt, setup.pypython
pom.xml, build.gradle, build.gradle.ktsjava
rockspec, .luacheckrc, init.lualua
None of the abovedefault

Also determine the project name from the current directory name.

Tell the user what you detected and ask them to confirm or override. If their stack isn't listed above, let them know they can define a custom stack.

Step 2: Check for Deprecated Dockerfiles

Check if .tsk/dockerfiles/ exists. If it does, warn the user:

Deprecated: tsk no longer supports filesystem-based dockerfiles in .tsk/dockerfiles/. Docker customization is now done via setup fields in tsk.toml. This guide will help you migrate to the new format.

List any files found in .tsk/dockerfiles/ and note their contents — you will use them to populate the new config.

Step 3: Choose Configuration Location

Ask the user where to put the configuration:

  • Project-level (.tsk/tsk.toml): Checked into version control, shared with the team. Best for project-specific dependencies that all contributors need.
  • User-level (~/.config/tsk/tsk.toml): Personal settings, not shared. Best for machine-specific paths, personal preferences, or settings across multiple projects.

If the user picks user-level, config goes under [project.<project-name>] in ~/.config/tsk/tsk.toml. If project-level, config goes at the top level of .tsk/tsk.toml.

Step 4: View the Current Docker Build

Run this command and show the output to the user:

bash
tsk docker build --dry-run

Explain to the user: this shows the complete Dockerfile that tsk generates with all layers resolved. Look for comments like # Stack layer, # Project layer, and # Agent layer to see where each setup field injects content. The next step will help them add the right customizations.

Step 5: Populate Configuration

Based on the project analysis, write the tsk.toml configuration. Use the layer reference below to decide what goes where.

tsk Docker Layer Architecture

tsk builds container images using 4 layers, assembled in this order:

1. Base layer    — Ubuntu 25.10, git, build-essential, ripgrep, Python 3, uv, podman
2. Stack layer   — Language runtime and tools (e.g., Go, Rust, Node.js)
3. Project layer — Project-specific system dependencies
4. Agent layer   — AI agent installation (Claude, Codex)

You customize layers 2-4 via tsk.toml:

Config fieldLayerPurpose
stack_config.<stack>.setupStack (2)Language tooling, compilers, package managers
setupProject (3)Project-specific apt packages, system libraries, custom tools
agent_config.<agent>.setupAgent (4)Agent-specific setup (rarely needed)

Each setup field contains raw Dockerfile commands (RUN, ENV, COPY, etc.) that get injected into the generated Dockerfile at the corresponding layer position. Setup commands run as the agent user by default. Use USER root to switch to root for operations that require it (e.g., apt-get), and always switch back to USER agent afterwards.

Built-in Stacks (What's Already Included)

tsk has built-in stack layers. You only need stack_config if the built-in is insufficient.

rust: Rust stable via rustup, CARGO_TARGET_DIR=/home/agent/.cargo/target

go: Go 1.25.0, GOPATH=/home/agent/gopath, CGO_ENABLED=0

node: Node.js LTS, npm, pnpm, yarn, typescript, ts-node, nodemon, eslint, prettier, jest, npm-check-updates. NODE_ENV=development

python: uv venv at /home/agent/.venv, pytest, pip, black, ruff, ty, mypy, poetry

java: OpenJDK 17, Maven, Gradle. Maven settings.xml and Gradle gradle.properties are pre-configured to route through the tsk proxy

lua: LuaJIT, Lua 5.1 dev libs, Neovim, stylua, LuaRocks with luacheck/busted/luassert/luafilesystem/nlua

default: Empty (base layer only)

Base Layer (Always Present)

Every container includes: Ubuntu 25.10, git, git-lfs, build-essential, curl, jq, just, ripgrep, sudo, Python 3, uv, podman (for DIND), and an agent user (UID 1000).

Configuration Format

Project-level (.tsk/tsk.toml):

toml
# Project-specific dependencies (injected at the project layer)
setup = '''
USER root
RUN apt-get update && apt-get install -y libssl-dev pkg-config cmake
USER agent
'''

# Override or extend the stack layer
[stack_config.rust]
setup = '''
RUN cargo install cargo-nextest sccache
ENV RUSTC_WRAPPER=sccache
'''

User-level (~/.config/tsk/tsk.toml):

toml
# Default settings for all projects
[defaults]
memory_gb = 16.0
cpu = 8

# Per-project overrides
[project.my-project]
stack = "rust"
setup = '''
USER root
RUN apt-get update && apt-get install -y libssl-dev pkg-config
USER agent
'''

[project.my-project.stack_config.rust]
setup = '''
RUN cargo install cargo-nextest
'''
Common Examples

Rust project needing system libraries:

toml
setup = '''
USER root
RUN apt-get update && apt-get install -y \
    libssl-dev pkg-config cmake protobuf-compiler
USER agent
'''

Python project with native dependencies:

toml
setup = '''
USER root
RUN apt-get update && apt-get install -y \
    libpq-dev libffi-dev
USER agent
'''

Node.js project needing native build tools:

toml
setup = '''
USER root
RUN apt-get update && apt-get install -y \
    libcairo2-dev libjpeg-dev libpango1.0-dev libgif-dev
USER agent
'''

Go project with CGO and protocol buffers:

toml
[stack_config.go]
setup = '''
USER root
ENV CGO_ENABLED=1
RUN apt-get update && apt-get install -y protobuf-compiler
USER agent
RUN go install google.golang.org/protobuf/cmd/protoc-gen-go@latest
'''

Java project with a specific JDK version:

toml
[stack_config.java]
setup = '''
USER root
RUN apt-get update && apt-get install -y openjdk-21-jdk
USER agent
ENV JAVA_HOME=/usr/lib/jvm/java-21-openjdk-amd64
'''

Adding a stack not built into tsk (e.g., Scala):

toml
stack = "scala"

[stack_config.scala]
setup = '''
USER root
RUN apt-get update && apt-get install -y openjdk-21-jdk
RUN curl -fL https://github.com/coursier/coursier/releases/latest/download/cs-x86_64-pc-linux.gz | gzip -d > /usr/local/bin/cs \
    && chmod +x /usr/local/bin/cs \
    && cs setup --yes
USER agent
ENV JAVA_HOME=/usr/lib/jvm/java-21-openjdk-amd64
'''
Show full SKILL.md (422 more words)Show less
Writing Good Setup Commands
  • Setup commands run as the agent user (UID 1000) by default. Use USER root when you need elevated privileges (e.g., apt-get install), and always switch back to USER agent afterwards
  • Always combine apt-get update with apt-get install in the same RUN to avoid stale caches
  • Use -y flag for non-interactive installs
  • Combine related commands with && to reduce layers
  • Environment variables set with ENV persist into the running container
  • The project layer runs BEFORE the agent layer, so project setup cannot depend on agent tools
Deciding What Goes Where

Ask yourself:

  • Is it a language runtime or dev tool? → stack_config.<stack>.setup
  • Is it a system library or project dependency? → setup (project layer)
  • Does it modify how the AI agent works? → agent_config.<agent>.setup (rare)
  • Would it be useful for other projects with the same stack? → stack_config in user-level [defaults]
  • Is it specific to this project? → setup in .tsk/tsk.toml

Write the configuration file based on the project's needs. If there were deprecated dockerfiles found in step 2, migrate their contents to the appropriate setup fields.

If the user does not have specific customization needs yet, write a minimal config with just the stack field set and an empty setup with a comment explaining where to add dependencies.

Step 6: Test the Configuration

Run this command to verify the Docker image builds successfully and tasks work:

bash
tsk run -t ack

This creates a minimal task that just says "ack" and exits. If it completes successfully, the Docker configuration is working. If it fails, examine the error output:

  • Build failures: Usually a bad RUN command in a setup field. Check the Dockerfile output for the failing line.
  • Missing dependencies at runtime: The setup command succeeded but the tool isn't available. Check PATH and ENV settings.
  • Permission errors: May need USER root before install commands.

If the build fails, help the user fix the configuration and re-run tsk run -t ack.

If the user is stuck and cannot get their project working after multiple attempts, ask if they'd like to file a bug report against tsk. If they agree:

  1. Capture the output of tsk docker build --dry-run
  2. Capture the error message from the failing build or run
  3. Ask the user to briefly describe what aspect of their project is causing problems (e.g., specific system libraries, unusual toolchain, network requirements)
  4. File the issue using gh:
bash
gh issue create --repo dtormoen/tsk-tsk \
  --title "Docker build failure: <short description>" \
  --body "$(cat <<'EOF'
## Problem

<user's description of what aspect of their project causes problems>

## Error
<error output>
```

Generated Dockerfile (tsk docker build --dry-run)

dockerfile
<dry-run output>

EOF )"


## Additional Configuration Options

After the basic setup works, mention these optional settings the user might want:

```toml
# Forward host ports to containers (e.g., local databases)
host_ports = [5432, 6379]

# Mount volumes for build caches
volumes = [
    { host = "~/.cache/go-mod", container = "/go/pkg/mod" },
    { name = "build-cache", container = "/home/agent/.cache" },
]

# Pass environment variables to containers
env = [
    { name = "DB_PORT", value = "5432" },
]

# Container resources
memory_gb = 16.0
cpu = 8

# Enable Docker-in-Docker
dind = true

# Enable passwordless sudo inside containers
sudo = false

# Run containers in privileged mode (disables security restrictions)
privileged = false

# Expose host devices to containers (supports glob patterns)
devices = ["/dev/video0", "/dev/ttyUSB*"]

Note: To connect to host services via forwarded ports, use the TSK_PROXY_HOST environment variable (set automatically by tsk) as the hostname, not localhost.

© dtormoen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/tsk-config/skills/tsk-config of dtormoen/tsk-tsk.

Open the folder on GitHubat commit bc0c0c6

Compare with similar skills

Tsk Config next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Tsk Config compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tsk Config this skilldtormoen/tsk-tsk171—~2.8kAutomated safety check: NotesMIT
GreptimeDB Dev Docker ImageGreptimeTeam/greptimedb6.7k—~4kAutomated safety check: NotesApache-2.0
GitHub Actions CreatorFNOSP/FlyNarwhal4951 repos~2.4kAutomated safety check: PassAGPL-3.0
Frb Dockerfzyzcjy/flutter_rust_bridge5.4k—~914Automated safety check: PassMIT
Tokf Runmpecan/tokf199—~571Automated safety check: PassMIT
Check Cross Runtimeayutaz/piper-plus220—~3.5kAutomated safety check: PassMIT

Similar skills

  • GreptimeDB Dev Docker Image

    GreptimeTeam/greptimedb

    Packages a locally built GreptimeDB debug binary into a development-only Docker image for local-cluster testing, with an optional push to a dev registry.

    6.7k GitHub stars~4k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • GitHub Actions Creator

    FNOSP/FlyNarwhal

    A skill your agent uses when the user wants to create, generate, or set up a GitHub Actions workflow.

    495 GitHub starsUsed in 1 repo~2.4k tokens
    DevOps & CloudAuto-check passed
  • Frb Docker

    fzyzcjy/flutter_rust_bridge

    A skill your agent uses for ordinary flutterrustbridge Docker/devcontainer setup, local image usage, and Apple Silicon containers; route image upgrades and publishing to frb-upgrade-docker.

    5.4k GitHub stars~914 tokensUpdated today
    DevOps & CloudAuto-check passed
  • Tokf Run

    mpecan/tokf

    Compress verbose CLI output with tokf before returning results.

    199 GitHub stars~571 tokensUpdated today
    DevOps & CloudAuto-check passed
  • Check Cross Runtime

    ayutaz/piper-plus

    Python canonical (src/pythonrun/piperplus/, src/python/pipertrain/, src/python/g2p/piperplusg2p/) を変更した PR で、 ONNX I/O 以外の追随漏れ (phonemizer / config schema / CLI flag / data 形式 / API 変更) を 7 ランタイム +…

    220 GitHub stars~3.5k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Release

    matrixorigin/memoria

    Cut a Memoria release. An agent skill from matrixorigin/memoria.

    608 GitHub stars~494 tokensUpdated today
    DevOps & CloudAuto-check passed

More from dtormoen/tsk-tsk

  • Tsk Help

    dtormoen/tsk-tsk

    A skill your agent uses when the user asks about tsk commands, delegating development tasks to AI agents, managing sandboxed task execution, or working with the tsk task queue and server.

    171 GitHub stars~760 tokensUpdated 2 mo ago
    Auto-check passed
  • Tsk Add

    dtormoen/tsk-tsk

    Queue a single task based on the current conversation using tsk add

    171 GitHub stars~1k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Categories

Questions about Tsk Config

What does Tsk Config do?

A skill your agent uses when the user wants to set up or configure tsk Docker container images, customize their tsk.toml for Docker builds, configure stack/agent/project layers, or troubleshoot tsk…. Tsk Config is an agent skill from dtormoen/tsk-tsk.toml for Docker builds, configure stack/agent/project layers, or troubleshoot tsk container build issues.

When should I use Tsk Config?

Tsk Config fits situations like: the user wants to set up; configure tsk Docker container images; customize their tsk.toml for Docker builds; configure stack/agent/project layers.

How do I install Tsk Config in Claude Code?

Run `npx skills add dtormoen/tsk-tsk --skill tsk-config -a claude-code`. Or copy the skill folder (skills/tsk-config/skills/tsk-config in dtormoen/tsk-tsk) into .claude/skills/tsk-config in your project. Claude Code loads it when a task matches its description.

How do I install Tsk Config in Codex?

Run `npx skills add dtormoen/tsk-tsk --skill tsk-config -a codex`. Or copy the skill folder (skills/tsk-config/skills/tsk-config in dtormoen/tsk-tsk) into .agents/skills/tsk-config in your project. Codex loads it when a task matches its description.

Can I use Tsk Config in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dtormoen/tsk-tsk --skill tsk-config -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tsk-config, .gemini/skills/tsk-config, .github/skills/tsk-config and .opencode/skills/tsk-config in your project.

What does Tsk Config need to run?

Going by SKILL.md and its folder, Tsk Config needs the command-line tools its instructions call (apt-get and gh). Our summary lists: Python 3; Node.js; Docker. Its frontmatter pre-approves these tools: Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion.

Does Tsk Config access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Tsk Config safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Tsk Config use?

Tsk Config is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tsk Config use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Tsk Config?

Skills that share tags, products or a category with Tsk Config: GreptimeDB Dev Docker Image (GreptimeTeam/greptimedb, 6.7k stars), GitHub Actions Creator (FNOSP/FlyNarwhal, 495 stars), Frb Docker (fzyzcjy/flutter_rust_bridge, 5.4k stars) and Tokf Run (mpecan/tokf, 199 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tsk Config?

dtormoen (a GitHub user) maintains it in dtormoen/tsk-tsk, which has 171 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on July 29, 2026.

Source: dtormoen/tsk-tsk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.