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.
git clone --depth 1 https://github.com/koolamusic/claudefilesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/koolamusic/claudefiles/setup)<a href="https://agentmods.dev/commands/koolamusic/claudefiles/setup"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/koolamusic/claudefiles/setup"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.03290 |
| Opus 5.5 | $0.00010 | $0.01316 |
| Sonnet 5.5 | $0.00005 | $0.00658 |
| Haiku 4.5 | $0.00002 | $0.00329 |
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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
4. **If the feature has a `run:` list**: execute each command in order, from the repo root, after the `requires:` check has passed. These are the external tool's own installers, so they may write outside `<target>` (for How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your task
Install claudefiles by reading the manifest and deploying everything to the target directory.
Step 1: Read the manifest
Read claudefiles.yaml in this repo root. It declares what gets installed and how.
Step 2: Ask install target
Ask the user:
- Global (recommended): Install to
~/.claude/— available in all Claude Code sessions - Local: Install to
./.claude/in the current project only
Step 3: Detect platform
Determine if running on macOS or Linux to resolve the {{sound_player}} template variable:
- macOS →
afplay - Linux →
aplay
uname -s
Step 4: Create target directories
mkdir -p <target>/skills
mkdir -p <target>/commands
mkdir -p <target>/sounds
mkdir -p <target>/hooks
Step 5: Copy files
Copy the contents declared in install.targets.
Skills come with one exception: any skill directory named in an experimental feature's skills: list (e.g. tower) is opt-in and is copied in Step 8.5 only if the user enables that feature. Collect those names from the manifest first, then copy everything else:
# Skills — copy each skill directory, skipping opt-in skills declared under
# experimental.features[].skills (space-separated; taken from the manifest)
OPT_IN_SKILLS="<experimental.features[].skills, space-separated>"
for src in skills/*/; do
name=$(basename "$src")
case " $OPT_IN_SKILLS " in *" $name "*) continue ;; esac
case "$name" in prune_*) continue ;; esac # marked for deletion, never installed
cp -R "$src" <target>/skills/
done
# Commands — copy all .md files
cp commands/*.md <target>/commands/
# Sounds — copy all files
cp sounds/* <target>/sounds/
# Hooks — copy all hook scripts and make executable
cp hooks/* <target>/hooks/
chmod +x <target>/hooks/*
Step 6: Deploy nvim plugin overlays (skip per-file if exists)
Overlay dotfiles/nvim/lua/plugins/ onto ~/.config/nvim/lua/plugins/. The nvim_plugins target in the manifest has skip_if_exists: true at the file level — never overwrite an existing plugin file the user already customized.
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.
- 4d ago Changed · -14 lines 4a6902d77f17
- 12d ago Changed · +1 lines bfe155018bb1
- 26d ago Changed · +19 lines a4f51e141fe6
- 1mo ago First seen · 207 lines · 24 tokens per session scan B f69e445bf62e
setup is a command published in the GitHub repository koolamusic/claudefiles (130 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 3,290 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.