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 agents/open-horizon-labs/repo-native-alignment/worktree-setupgit clone --depth 1 https://github.com/open-horizon-labs/repo-native-alignmentWrote 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/agents/open-horizon-labs/repo-native-alignment/worktree-setup)<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/worktree-setup"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/worktree-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 5.1 | $0.00035 | $0.01889 |
| Opus 5 | $0.00017 | $0.00945 |
| Sonnet 5 | $0.00007 | $0.00378 |
| Haiku 4.5 | $0.00003 | $0.00189 |
Grade A, and why
worktree-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/worktree-setup
Bootstrap RNA in a git worktree so code navigation is fast and correct from the first tool call.
Invoke this skill at the start of any session that runs inside a worktree (i.e., when git worktree list shows more than one entry and the cwd is not the main checkout).
You are an RNA power user. Use RNA MCP tools (
search,repo_map,outcome_progress,list_roots) for all code navigation — never Grep or Read for code understanding. Every Grep/Read instead of an RNA tool is a friction event. Log it with/friction.
Quick setup (TL;DR)
# 1. Scan (fast — warm cache via prep-worktree.sh already ran)
repo-native-alignment scan --repo . 2>&1 | tail -2
# 2. Verify index is live
COUNT=$(repo-native-alignment search "" --repo . --limit 1 2>/dev/null | grep -o "[0-9]* symbols" | head -1)
echo "RNA: $COUNT indexed"
# If COUNT is 0 or missing → run full scan and investigate (see Step 2 below)
# 3. Navigate with RNA — never Grep/Read for code
mcp__rna-mcp__repo_map # orientation
mcp__rna-mcp__search # symbol / semantic search
Full process
Step 1: Scan the worktree
The worktree's .oh/.cache/ was seeded from the main repo's cache by scripts/prep-worktree.sh. The first scan is an incremental pass — it only re-indexes files that changed since the cache was copied.
repo-native-alignment scan --repo . 2>&1 | tail -2
Expected output (warm cache):
Scanned 312 files in 14s (12 changed, 300 cached)
Index ready.
If the script hasn't been run yet (cold start), run a full scan:
repo-native-alignment scan --repo . --full 2>&1 | tail -2
Full scans take 30–60 s for a typical Rust repo. Warm incremental scans take ~15 s.
Step 2: Verify the index is live
COUNT=$(repo-native-alignment search "" --repo . --limit 1 2>/dev/null | grep -o "[0-9]* symbols" | head -1)
echo "RNA: $COUNT indexed"
If COUNT is 0 or the command errors:
- Run a forced full scan:
repo-native-alignment scan --repo . --full 2>&1 - Verify the binary is on
$PATH:which repo-native-alignment 2>/dev/null \ || ls target/release/repo-native-alignment 2>/dev/null \ || ls target/debug/repo-native-alignment 2>/dev/null - Check that
--repo .resolves to the worktree root (not the main checkout).
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.
- 5d ago First seen · 192 lines · 35 tokens per session scan A f1345103505f
worktree-setup is an agent published in the GitHub repository open-horizon-labs/repo-native-alignment (4 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,889 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.