agentmods.dev

tsk-tsk CLAUDE.md

Repository-specific instructions for Claude Code, an AI coding assistant. They explain the project’s architecture, important files, commands, and development workflow.

In plain words
What is it for?
Use them when adding features, fixing bugs, reviewing code, or running the project’s task and testing workflows.
Why use it?
They give the assistant the project context it needs to make changes that fit the existing code and practices.

Instructions file

170 1mo ago A scan 1,695 tokens original MIT
View the source file dtormoen/tsk-tsk
Install

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.

agentmods
npx agentmods add instructions/dtormoen/tsk-tsk/claude-md
Clone the repo
git clone --depth 1 https://github.com/dtormoen/tsk-tsk
Per session 1,695 This file is loaded in full into every session.
When invoked 1,695 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01695 $0.01695
Opus 5 $0.00847 $0.00847
Sonnet 5 $0.00339 $0.00339
Haiku 4.5 $0.00169 $0.00169

Measured yesterday against content hash 0f9992215d23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tsk-tsk CLAUDE.md 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 yesterday.

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.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Important files:

  • @justfile - key development commands. These should be used when possible over raw cargo commands.
  • @README.md - user facing documentation for the project. This could cover key user facing details without going into too much detail. Make sure it stays up to date with your changes.

Architecture Overview

tsk implements a command pattern with dependency injection for testability. The core workflow: queue tasks → execute in containers (Docker or Podman) → create git branches for review. tsk can run in server mode for continuous task processing across multiple repositories.

Key Components

  • CLI Commands (src/commands/): Command handlers for all tsk subcommands. See README.md for the full command reference.
  • Task Management (src/task.rs, src/context/task_storage.rs, src/task_manager.rs, src/task_runner.rs): TaskBuilder for task creation, SQLite-backed TaskStorage, task lifecycle (Queued → Running → Complete/Failed/Cancelled). Two execution paths: server-scheduled (via add) and inline (via run/shell).
  • Docker Integration (src/docker/): DockerImageManager (layered image builds: base → stack → project → agent), ProxyManager (proxy lifecycle with per-configuration instances), DockerManager (container execution). Security-first with dropped capabilities and per-container network isolation.
  • Server Mode (src/server/): TskServer daemon with TaskScheduler and WorkerPool for parallel task execution. Parent-aware scheduling, cascading failure handling, and auto-cleanup of old tasks.
  • TUI (src/tui/): Interactive terminal dashboard using ratatui/crossterm. Two-panel layout (task list + log viewer) with ServerEvent channel from scheduler.
  • Git Operations (src/git.rs, src/git_sync.rs, src/git_operations.rs, src/repo_utils.rs): Repository cloning with configurable copy mode (CopyMode: working directory overlay or committed-only), branch creation, result fetching. Uses git CLI (not libgit2) for commits and post-overlay renormalization to support clean/smudge filters (e.g., Git LFS). GitSyncManager for concurrent access safety. Supports submodules, git worktrees, and Git LFS.
  • Storage/Config (src/context/): AppContext (DI container), TskEnv (directory paths), TskConfig (user/project config with layered resolution). See README.md for config file reference.
  • Agents (src/agent/): Agent trait for AI agent integration (claude, codex, integ, no-op). Handles command building, validation, warmup, and version tracking.
  • Auto-Detection (src/repository.rs): Stack detection from project files and project name from directory name.
  • Skills Marketplace (skills/, .claude-plugin/marketplace.json): Claude Code skills following the Agent Skills open standard.

Read the full file on GitHub · 85 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. yesterday First seen · 85 lines · 1,695 tokens per session scan A 0f9992215d23

Subscribe to this mod's changes

tsk-tsk CLAUDE.md is an instructions file published in the GitHub repository dtormoen/tsk-tsk (170 stars, last pushed 1mo ago), licensed MIT. It adds 1,695 tokens to every session, about $0.0085 per session on Opus 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 2026-08-30.

DebuggingPlanningTestingagentic-codingagentsaiai-agentsai-agents-automationclaude-code
Related

Other instructions, from other repositories

rowboat CLAUDE.md

Instructions for rowboatlabs/rowboat, covering claude.md - ai coding agent context, quick reference commands, electron app (apps/x), monorepo structure and electron app architecture (apps/x).

rowboatlabs/rowboat · 1,818 tokens

claude-code-tresor CLAUDE.md

Instructions for alirezarezvani/claude-code-tresor, covering claude.md - development guide, 🎯 repository purpose, 🏗️ architecture, 🛠️ common development commands and building & testing.

alirezarezvani/claude-code-tresor · 5,338 tokens

loom CLAUDE.md

Instructions for cosmix/loom, covering claude.md, project overview, build commands, architecture and source layout (loom/src/).

cosmix/loom · 1,323 tokens

cybara CLAUDE.md

Instructions for metaspartan/cybara, covering ai coding rules for cybara agent platform, no code comments (strict), runtime environment, import rules and ✅ do.

metaspartan/cybara · 1,479 tokens

cybara AGENTS.md

Instructions for metaspartan/cybara, covering cybara agent rules, package manager policy (strict), command translation, typescript type safety and no comments.

metaspartan/cybara · 1,010 tokens

zerostack AGENTS.md

AGENTS.md instructions for gi-dellav/zerostack, a project described as: Lightweight coding agent written in Rust, optimized for memory footprint and performance.

gi-dellav/zerostack · 115 tokens