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/ai-native-sys/claude-code-tools/uninstallnpx skills add ai-native-sys/claude-code-tools --skill uninstallgit clone --depth 1 https://github.com/ai-native-sys/claude-code-toolsWhat 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 | $0.00016 | $0.00450 |
| Opus 5 | $0.00008 | $0.00225 |
| Sonnet 5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade D, and why
uninstall scanned grade D 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. Remove the `statusLine` entry from `~/.claude/settings.json` Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.claude/plugins/claude-code-tools/hud/cache What it actually says
Uninstall claude-code-tools HUD
Guide the user through cleanly removing the HUD statusline plugin.
Step 1: Confirm with user
Tell the user this will:
- Remove the
statusLineentry from~/.claude/settings.json - Delete HUD config, cache, and log files from
~/.claude/plugins/claude-code-tools/hud/
Ask the user to confirm before proceeding. Also ask if they want to keep their config file in case they reinstall later.
Step 2: Remove statusLine from settings
- Read
~/.claude/settings.json - Check if the
statusLinefield exists and contains a reference tohud(look forclaude-code-tools/hudin the command string) - If it matches, remove the
statusLinefield entirely. Do NOT remove it if it points to a different statusline plugin (e.g.,claude-hud). - Preserve all other settings and write back.
If the statusLine doesn't reference our hud plugin, inform the user and skip this step.
Step 3: Clean up data files
Remove the HUD data directory:
rm -rf ~/.claude/plugins/claude-code-tools/hud/cache
rm -rf ~/.claude/plugins/claude-code-tools/hud/logs
If the user chose to keep their config, skip deleting the config file. Otherwise:
rm -f ~/.claude/plugins/claude-code-tools/hud/config.json
If the directory is now empty, remove it:
rmdir ~/.claude/plugins/claude-code-tools/hud 2>/dev/null
Step 4: Report result
Tell the user the HUD statusline has been removed. The statusline will disappear on the next Claude Code render cycle (no restart needed).
If they want to reinstall later, they can run /hud:setup again.
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.
- yesterday First seen · 55 lines · 16 tokens per session scan D 4788e7319ce7
uninstall is a skill published in the GitHub repository ai-native-sys/claude-code-tools (1 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 450 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.