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/lucasduys/forge/setup-toolsgit clone --depth 1 https://github.com/LucasDuys/forgeWhat 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 | $0.00011 | $0.01125 |
| Opus 5 | $0.00005 | $0.00562 |
| Sonnet 5 | $0.00002 | $0.00225 |
| Haiku 4.5 | $0.00001 | $0.00112 |
Grade A, and why
setup-tools scanned grade A with 0 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Setup Tools
Detect which CLI tools are available on the system, show which are missing, and offer to install them.
Step 1: Run Detection
Run version checks for all supported CLI tools:
echo "=== CLI Tool Detection ==="
tools_status=""
check_tool() {
local name="$1" cmd="$2" install="$3" purpose="$4"
if eval "$cmd" > /dev/null 2>&1; then
version=$(eval "$cmd" 2>/dev/null | head -1)
tools_status="${tools_status}\n [installed] ${name} — ${purpose} (${version})"
else
tools_status="${tools_status}\n [missing] ${name} — ${purpose}\n Install: ${install}"
fi
}
check_tool "gh" "gh --version" "winget install GitHub.cli" "GitHub PR/issue management, CI/CD"
check_tool "vercel" "vercel --version" "npm i -g vercel" "Deployment, preview URLs, serverless"
check_tool "stripe" "stripe --version" "winget install Stripe.StripeCLI" "Payment testing, webhooks"
check_tool "ffmpeg" "ffmpeg -version" "winget install Gyan.FFmpeg" "Video/audio processing"
check_tool "playwright" "npx playwright --version" "npm i -g playwright && playwright install" "Browser automation, E2E testing"
check_tool "gws" "gws --version" "npm i -g @googleworkspace/cli" "Google Workspace — Drive, Gmail, Sheets"
check_tool "notebooklm" "notebooklm --version" "pip install notebooklm-py" "Research with grounded citations"
check_tool "supabase" "supabase --version" "winget install Supabase.CLI" "Database, auth, edge functions"
check_tool "firebase" "firebase --version" "npm i -g firebase-tools" "App hosting, Firestore, cloud functions"
check_tool "docker" "docker --version" "winget install Docker.DockerDesktop" "Container management"
check_tool "wrangler" "wrangler --version" "npm i -g wrangler" "Cloudflare Workers, KV"
check_tool "graphify" "graphify -h" "pip install graphifyy" "Codebase knowledge graphs for architecture-aware planning"
check_tool "cli-anything" "ls ~/.claude/plugins/cli-anything* 2>/dev/null || compgen -c cli-anything- | head -1" "In Claude Code: /plugin marketplace add HKUDS/CLI-Anything && /plugin install cli-anything" "Agent-native CLIs for desktop software"
echo -e "$tools_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 · 100 lines · 11 tokens per session scan A a8e957810f73
setup-tools is a command published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,125 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
discover
Run a full user research cycle — persona creation, empathy mapping, and journey mapping for a product or feature.
test-plan
Run the full usability study workflow — research questions, participant criteria, tasks, metrics, and facilitation guide.
eg-new-feature
Build a new feature using the elephant/goldfish workflow — design doc, goldfish design check, implement, review, validate.
eg-precommit-review
Run the pre-commit independent-reviewer loop on the current branch's pending changes.
eg-fix-bug
Fix a bug using the elephant/goldfish workflow — problem doc, goldfish diagnosis check, failing test, fix, review, validate.
verify-custom-rules
Verify custom rules for Safety Net.