Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/architonixlabs/RepoOrchnpx agentmods add commands/architonixlabs/repoorch/repo-orch-setupWrote 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/architonixlabs/repoorch/repo-orch-setup)<a href="https://agentmods.dev/commands/architonixlabs/repoorch/repo-orch-setup"><img src="https://agentmods.dev/badge/commands/architonixlabs/repoorch/repo-orch-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/architonixlabs/repoorch/repo-orch-setup"><img src="https://agentmods.dev/badge/commands/architonixlabs/repoorch/repo-orch-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 | $0.00059 | $0.02639 |
| Opus 5 | $0.00030 | $0.01319 |
| Sonnet 5 | $0.00012 | $0.00528 |
| Haiku 4.5 | $0.00006 | $0.00264 |
Grade B, and why
repo-orch-setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
at_cfg=$(grep -os '"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS"[[:space:]]*:[[:space:]]*"1"' .claude/settings.json 2>/dev/null || echo "") How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/repo-orch-setup
Guided first-time install for repo-orchestrator. Run once from your workspace root.
Design (read once): this flow is Claude-native and needs no build step — it always works, even with no Node toolchain. Optional tiers (indexer, MCP server) enhance the experience but never block reaching a working state. The irreducible result of setup is a bootstrapped workspace via /repo-orch-init; everything else is progressive enhancement.
Step 0 — Optional accelerator (skip if unsure)
If a compiled setup runner is already built at .claude/plugins/repo-orchestrator/setup/dist/index.js, you MAY run it for a richer task-list UI:
node .claude/plugins/repo-orchestrator/setup/dist/index.js
If you run it, skip to Step 5 afterward. If it is not present, do NOT build it just to run it — continue with the steps below. They are the primary path and are fully sufficient. (The runner is only ever a convenience; it is never on the critical path to a working install.)
Step 1 — Scan environment (one Bash call)
Execute this single Bash script. Capture the output — do not surface raw output to the user.
#!/usr/bin/env bash
set -euo pipefail
cc_ver=$(claude --version 2>/dev/null | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' | head -1 || echo "")
if [ -z "$cc_ver" ]; then cc_status="MISSING"; cc_detail="not found on PATH"
elif [ "$cc_ver" = "2.1.32" ]; then cc_status="OK"; cc_detail="v$cc_ver"
elif printf '%s\n%s\n' "2.1.32" "$cc_ver" | sort -V -C 2>/dev/null; then cc_status="OK"; cc_detail="v$cc_ver"
else cc_status="OLD"; cc_detail="v$cc_ver (needs 2.1.32+)"; fi
at_env=$(printenv CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS 2>/dev/null || echo "")
at_cfg=$(grep -os '"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS"[[:space:]]*:[[:space:]]*"1"' .claude/settings.json 2>/dev/null || echo "")
if [ "$at_env" = "1" ] || [ -n "$at_cfg" ]; then at_status="OK"; at_detail="enabled"
else at_status="OPTIONAL"; at_detail="not set"; fi
node_ver=$(node --version 2>/dev/null | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' | head -1 || echo "")
if [ -z "$node_ver" ]; then node_status="OPTIONAL"; node_detail="not installed"
elif [ "$(echo "$node_ver" | cut -d. -f1)" -ge 18 ]; then node_status="OK"; node_detail="v$node_ver"
else node_status="OLD"; node_detail="v$node_ver (needs 18+)"; fi
npm_ver=$(npm --version 2>/dev/null || echo "")
if [ -z "$node_ver" ]; then npm_status="SKIP"; npm_detail="skipped"
elif [ -n "$npm_ver" ]; then npm_status="OK"; npm_detail="v$npm_ver"
else npm_status="MISSING"; npm_detail="not found"; fi
pp=".claude/plugins/repo-orchestrator"
if [ -f "$pp/indexer/dist/index.js" ]; then t1_status="OK"; t1_detail="built"
elif [ -n "$node_ver" ]; then t1_status="OPTIONAL"; t1_detail="not built"
else t1_status="SKIP"; t1_detail="skipped"; fi
if [ -f "$pp/mcp/dist/server.js" ]; then t2_status="OK"; t2_detail="built"
elif [ -n "$node_ver" ]; then t2_status="OPTIONAL"; t2_detail="not built"
else t2_status="SKIP"; t2_detail="skipped"; fi
mcp_wired=$(grep -os '"repo-orchestrator"' .claude/settings.json 2>/dev/null || echo "")
if [ -n "$mcp_wired" ]; then mcp_status="OK"; mcp_detail="wired into settings.json"
elif [ -f "$pp/mcp/dist/server.js" ]; then mcp_status="OPTIONAL"; mcp_detail="built but not wired"
else mcp_status="SKIP"; mcp_detail="skipped"; fi
git_count=0; git_names=""
for d in */; do
[ -d "${d}.git" ] && git_count=$((git_count+1)) && git_names="$git_names ${d%/}"
done
git_names="${git_names# }"
if [ "$git_count" -ge 1 ]; then ws_status="OK"; ws_detail="$git_count repo(s): $git_names"
else ws_status="MISSING"; ws_detail="no git repos found"; fi
cat <<EOF
CC_STATUS=$cc_status|$cc_detail
AT_STATUS=$at_status|$at_detail
NODE_STATUS=$node_status|$node_detail
NPM_STATUS=$npm_status|$npm_detail
T1_STATUS=$t1_status|$t1_detail
T2_STATUS=$t2_status|$t2_detail
MCP_STATUS=$mcp_status|$mcp_detail
WS_STATUS=$ws_status|$ws_detail
WS_COUNT=$git_count
WS_NAMES=$git_names
EOF
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.
- 10d ago First seen · 200 lines · 59 tokens per session scan B 8b8ace98ee3f
repo-orch-setup is a command published in the GitHub repository architonixlabs/RepoOrch (3 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 2,639 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
create
Scaffold a new plugin with directory structure, manifests, and marketplace registration.
bugfix
TDD-driven bugfix workflow: tester writes failing test (RED) → developer fixes (GREEN) → developer refactors (REFACTOR) → reviewer validates. Accepts issue number, description, or both. Auto-creates PR unless --no-pr flag is passed.
develop
Implement skill development issues with TDD-governed workflow.
update
Update the swarm plugin to the latest version.
launch
Interactively launch an agent team with guided setup.
dev-task
Create an agent team to develop: Developer teammate + Code-tester teammate + QA-tester teammate + Reviewer teammate + Researcher subagent → implements .dev/cdt/plans/plan-$TIMESTAMP.md in waves.