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/setupnpx skills add ai-native-sys/claude-code-tools --skill setupgit 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 | $0.00015 | $0.01378 |
| Opus 5 | $0.00008 | $0.00689 |
| Sonnet 5 | $0.00003 | $0.00276 |
| Haiku 4.5 | $0.00002 | $0.00138 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/plugins/claude-code-tools/hud/logs/hud.log How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup claude-code-tools HUD
Guide the user through configuring the HUD statusline plugin step by step.
Step 1: Check existing config
Read ~/.claude/plugins/claude-code-tools/hud/config.json to see if there's an existing configuration. If a config already exists, show the user the current settings and ask if they want to reconfigure.
Step 2: Detect runtime
Check if bun is available (run which bun), otherwise fall back to node. Store the runtime choice for the command.
Step 3: Register the statusline
The HUD plugin works by configuring the statusLine field in ~/.claude/settings.json. Claude Code invokes this command every ~300ms, piping session JSON to stdin, and renders stdout as the statusline.
IMPORTANT — auto-update safe path resolution:
The plugin source code is cached at ~/.claude/plugins/cache/claude-code-tools/hud/<version>/. When the plugin updates, a new version directory is created. A hardcoded path would break on update. The statusLine command MUST dynamically resolve to the latest version.
Use this command pattern (replace node with bun if detected):
bash -c '"node" "$(ls -td ~/.claude/plugins/cache/claude-code-tools/hud/*/src/hud.mjs 2>/dev/null | head -1)"'
This finds the most recently modified version directory at runtime, so plugin updates work automatically without re-running setup.
Steps:
- Read existing
~/.claude/settings.json(create if it doesn't exist). - Set the
statusLinefield to the dynamic command string. Preserve all other existing settings. - Write back the updated
~/.claude/settings.json.
Example settings.json entry:
{
"statusLine": "bash -c '\"node\" \"$(ls -td ~/.claude/plugins/cache/claude-code-tools/hud/*/src/hud.mjs 2>/dev/null | head -1)\"'"
}
Step 4: Configure segments
Ask the user which segments they want to enable. Default is all segments:
- model — Model name (e.g., "Opus 4.6")
- billing — Subscription type badge ([API], [Pro], [Max])
- workspace — Current directory name + worktree indicator
- git — Branch name + diff stats (+insertions/-deletions)
- context — Context window usage bar with percentage
- quota — 5-hour and 7-day rate limit usage (Pro/Max only), with reset countdown
- speed — Output tokens per second
- cost — Estimated session cost (API users)
- agents — Running background agent status
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 · 125 lines · 15 tokens per session scan B f1577def65b5
setup is a skill published in the GitHub repository ai-native-sys/claude-code-tools (1 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 1,378 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
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…