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/zapat-ai/zapat/setupgit clone --depth 1 https://github.com/zapat-ai/zapatWrote 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/zapat-ai/zapat/setup)<a href="https://agentmods.dev/commands/zapat-ai/zapat/setup"><img src="https://agentmods.dev/badge/commands/zapat-ai/zapat/setup.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.05125 |
| Opus 5 | $0.00000 | $0.02563 |
| Sonnet 5 | $0.00000 | $0.01025 |
| Haiku 4.5 | $0.00000 | $0.00513 |
Grade C, and why
setup scanned grade C with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get update && sudo apt-get install -y tmux jq gh nodejs npm git curl Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/settings.json 2>/dev/null | jq -r '.env.CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS // empty' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl --version This is a copy
91% identical to zapat — 122 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 580 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zapat Setup Wizard
You are guiding a user through setting up Zapat, an autonomous dev pipeline powered by Claude Code. Walk through each step interactively, asking questions and validating as you go.
Step 0 — Locate or Install Zapat
First, determine where Zapat is installed.
# Check for existing installation
if [ -n "$ZAPAT_HOME" ] && [ -d "$ZAPAT_HOME" ]; then
echo "FOUND:$ZAPAT_HOME"
elif [ -d "$HOME/.zapat" ]; then
echo "FOUND:$HOME/.zapat"
elif [ -f "./bin/zapat" ] && [ -f "./package.json" ] && grep -q '"name": "zapat"' ./package.json 2>/dev/null; then
echo "FOUND:$(pwd)"
else
echo "NOT_FOUND"
fi
If NOT_FOUND:
Tell the user: "Zapat isn't installed yet. Let me set it up."
Ask where to install:
~/.zapat(recommended — keeps it out of your project directories)- Custom path (let them specify)
Clone the repository:
git clone https://github.com/zapat-ai/zapat.git <chosen_path>
Then set ZAPAT_HOME for the current session:
export ZAPAT_HOME=<chosen_path>
And add it to their shell profile for persistence:
# Detect shell profile
SHELL_PROFILE="$HOME/.zshrc"
[ -f "$HOME/.bashrc" ] && [ ! -f "$HOME/.zshrc" ] && SHELL_PROFILE="$HOME/.bashrc"
# Add ZAPAT_HOME if not already there
grep -q 'ZAPAT_HOME' "$SHELL_PROFILE" 2>/dev/null || echo 'export ZAPAT_HOME="<chosen_path>"' >> "$SHELL_PROFILE"
If FOUND:
Set ZAPAT_HOME to the found path for the rest of this session. Change into that directory:
cd $ZAPAT_HOME
If .env already exists in $ZAPAT_HOME, inform the user that Zapat is already configured and ask whether they want to:
- Re-run setup from scratch (backs up existing config first)
- Update specific sections (jump to that step)
- Cancel
All subsequent commands in this wizard should run from $ZAPAT_HOME.
Step 1 — System Prerequisites
Check that all required tools are installed. Run each check and report results:
tmux -V
jq --version
gh --version
node --version # Must be 18+
npm --version
git --version # Must be 2.20+
curl --version
claude --version
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.
- 3d ago First seen · 580 lines · 0 tokens per session scan C db597c419ab4
setup is a command published in the GitHub repository zapat-ai/zapat (11 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,125 tokens. A static security scan graded it C with 3 findings (asks for root, reads agent configuration directories, makes network calls). It is 91% identical to zapat, differing in 122 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.