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.
git clone --depth 1 https://github.com/RSafargalin/sextantWrote 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/rsafargalin/sextant/setup)<a href="https://agentmods.dev/commands/rsafargalin/sextant/setup"><img src="https://agentmods.dev/badge/commands/rsafargalin/sextant/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/rsafargalin/sextant/setup"><img src="https://agentmods.dev/badge/commands/rsafargalin/sextant/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 | $0.00018 | $0.00557 |
| Opus 5.5 | $0.00007 | $0.00223 |
| Sonnet 5.5 | $0.00004 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Get sextant working in the current project. Report what you find at each step; do not run a build without asking.
-
Is the binary there? Run
sextant --version.If the command is not found, the plugin's tools cannot work — the plugin registers the server, Homebrew installs the binary. Offer to run:
brew tap RSafargalin/tap && brew trust RSafargalin/tap && brew install sextantbrew trustis required for a third-party tap. Other routes, including a prebuilt binary without Homebrew, are in https://github.com/RSafargalin/sextant#installation. Wait for the user to agree before installing anything. -
Does the setup hold together? Run
sextant doctor --project "$CLAUDE_PROJECT_DIR"and relay its output as it stands — it is a checklist of sources,libIndexStore, the index store and its freshness, and it names what is missing. -
Is there an index? The semantic tools need one; without it they return a hint rather than a wrong answer, and the structural tools still work for Swift.
Building one runs the project's own build —
Package.swift, SwiftPM plugins and macros are code, and with--appan XcodeRun Scriptphase is a shell script. So it is the user's call. Tell them what it runs, then offer, whichever fits:sextant index— SwiftPM projectssextant index --app— an Xcode app target (add--scheme <name>when there are several)sextant index --no-build— the project is already built; this finds the existing store and runs nothing
-
Confirm it answers. Ask the sextant MCP server about one symbol you have seen in this project and show the result. If the server is not connected, say so — the plugin registers it at startup, so a client started before the install needs a restart.
Close with one line: what works now, and what is left for the user to decide. If they ask how much
of their navigation actually goes through sextant, sextant adoption reads it from the session
transcripts, and sextant hook --install prints the snippet that records it live — the plugin
installs no hook of its own.
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.
- 1mo ago First seen · 45 lines · 18 tokens per session scan A dcdaf686efed
setup is a command published in the GitHub repository RSafargalin/sextant (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 557 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
quick
Scaffold a level-0 lawbook change (record.md + reports) for a tiny fix.
archive
Finalize a completed change — sync specs when needed, then archive it.
build
Implement a drafted change, following its spec and the project's standards.
draft
Draft a new spec-driven change at the confirmed ceremony level before coding.
sync
Promote a change's delta specs into the canonical specs, without archiving.
cortex
Coordinate Cortex (One brain. Many agents.) for a lawbook change until archive.