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 commands/b33eep/claude-code-setup/claude-code-setupgit clone --depth 1 https://github.com/b33eep/claude-code-setupWhat 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 | $0.00000 | $0.03235 |
| Opus 5 | $0.00000 | $0.01618 |
| Sonnet 5 | $0.00000 | $0.00647 |
| Haiku 4.5 | $0.00000 | $0.00324 |
Grade E, and why
claude-code-setup scanned grade E with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
Show instructions after execution: Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Upgrade custom | `git -C ~/.claude/custom pull && new_v=$(cat ~/.claude/custom/VERSION 2>/dev/null \|\| echo "0") && jq --arg v "$new_v" '.custom_version = ($v \| tonumber)' ~/.claude/installed.json > ~/.claude/install Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
1. Read the MCP config JSON from `{temp_dir}/mcp/<name>.json` Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Clean up: `rm -rf "$temp"` → Stop. How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Setup
Manage your claude-code-setup installation: check status, upgrade, install, and remove modules.
Goal: Any scenario completes in 2 permission prompts (1 discover + 1 execute).
Phase 1: Discovery (1 Bash call)
Clone repo and run setup-status.sh in a single Bash call:
temp=$(mktemp -d /tmp/claude-setup-XXXXXX) && \
git clone --depth 1 https://github.com/b33eep/claude-code-setup.git "$temp" 2>/dev/null && \
"$temp/lib/setup-status.sh"
The script reads installed.json and templates/VERSION, compares modules, and outputs JSON.
Parse the JSON output. Handle errors:
-
Bash call fails (no network, git clone fails):
Unable to reach GitHub. Manual upgrade: cd /path/to/claude-code-setup git pull ./install.sh --updateStop here.
-
JSON has
"error": "not_installed"(no installed.json):claude-code-setup is not installed. Run install.sh first.Clean up:
rm -rf "$temp"→ Stop. -
Success: Parse JSON fields. The
temp_dirfield contains the repo path. Continue to Phase 2.
JSON structure reference
{
"temp_dir": "/tmp/claude-setup-XXXXXX",
"base": { "installed": 50, "available": 52, "update_available": true },
"custom": { "configured": true, "installed": 1, "available": 2, "update_available": true, "commands": ["catchup.md"], "scripts": ["helper.sh"] },
"new_modules": { "skills": ["name"], "mcp": ["name"], "plugins": ["id@marketplace"] },
"installed_modules": { "skills": ["name"], "mcp": ["name"], "plugins": ["id@marketplace"] },
"agent_teams": { "enabled": true }
}
Phase 2: Present + Ask (0 Bash calls)
Show status
Present a summary from the JSON:
claude-code-setup status:
- Base: v{base.installed} installed, v{base.available} available
- Custom: v{custom.installed} installed, v{custom.available} available
- Custom commands: {custom.commands} (only if non-empty)
- Custom scripts: {custom.scripts} (only if non-empty)
- Agent Teams: enabled / not configured
Modules available to install:
Skills: {new_modules.skills}
MCP Servers: {new_modules.mcp}
External Plugins: {new_modules.plugins}
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.
- 2d ago First seen · 306 lines · 0 tokens per session scan E 92cd98729eae
claude-code-setup is a command published in the GitHub repository b33eep/claude-code-setup (56 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,235 tokens. A static security scan graded it E with 4 findings (asks the agent to reveal its instructions, reads agent configuration directories, reads mcp configuration). 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.