What is motel AGENTS.md?

Project instructions for kitlangton/motel, a tool with a terminal interface, a local server, a background daemon, and commands for querying services, traces, spans, and logs. It also documents installation, development, restart, and test commands.

Use it to install dependencies, start or stop the daemon and terminal interface, run the server, query observability data, and run the test suite.

It puts the project's routine commands and verification steps in one place. Developers can use it to run the tool, manage its background process, inspect telemetry, and execute tests consistently.

motel AGENTS.md — Instructions file for Codex and OpenCode by kitlangton: Project instructions for kitlangton/motel, a tool with a terminal…

Install

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.

agentmods

npx agentmods add instructions/kitlangton/motel/agents-md

Clone the repo

git clone --depth 1 https://github.com/kitlangton/motel

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kitlangton/motel/agents-md.svg)](https://agentmods.dev/instructions/kitlangton/motel/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/kitlangton/motel/agents-md"><img src="https://agentmods.dev/badge/instructions/kitlangton/motel/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,617 This file is loaded in full into every session.

When invoked 3,617 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.03617	$0.03617
Opus 5	$0.01809	$0.01809
Sonnet 5	$0.00723	$0.00723
Haiku 4.5	$0.00362	$0.00362

Measured 4d ago against content hash 3d8dbf97962d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

motel AGENTS.md 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 4d 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.

AGENTS.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Commands

Install deps: bun install
Run the TUI: bun run dev or bun run start (auto-ensures a managed OTLP daemon is running in the background so traces ingest while the TUI is up)
Start the background daemon only: bun run daemon (same as motel start)
Stop the managed daemon: bun run stop
Daemon status JSON: bun run status
Restart daemon + relaunch TUI: bun run restart
Run the local server in the foreground (no daemon, no TUI): bun run server
Run tests: bun run test
Query services via CLI: bun run cli services
Query traces via CLI: bun run cli traces <service> [limit]
Query a span via CLI: bun run cli span <span-id>
Query spans for one trace: bun run cli trace-spans <trace-id>
Search spans via CLI: bun run cli search-spans [service] [operation] [parent=<operation>] [attr.key=value ...]
Search traces via CLI: bun run cli search-traces <service> [operation] [attr.key=value ...]
Query trace stats via CLI: bun run cli trace-stats <groupBy> <agg> [service] [attr.key=value ...]
Query logs via CLI: bun run cli logs <service>
Search logs via CLI: bun run cli search-logs <service> [body] [attr.key=value ...]
Query log stats via CLI: bun run cli log-stats <groupBy> [service] [attr.key=value ...]
Query logs for one trace: bun run cli trace-logs <trace-id>
Query logs for one span: bun run cli span-logs <span-id>
Query facets via CLI: bun run cli facets <traces|logs> <field>
Print Effect setup instructions: bun run instructions
Build the web UI: bun run web:build
Dev the web UI (with hot reload): bun run web:dev
Typecheck: bun run typecheck
Effect LSP diagnostics over the whole project: bunx effect-language-service diagnostics --project tsconfig.json --format text
Effect LSP interactive setup wizard: bunx effect-language-service setup

Release Strategy

npm package: @kitlangton/motel
Current published npm latest: 0.2.4 (npm view @kitlangton/motel dist-tags --json)
Tags are versioned as vX.Y.Z (git tag --sort=-version:refname shows v0.2.4, v0.2.3, ...)
Publishing is handled by GitHub Actions in .github/workflows/publish.yml, not by local manual npm publish
The publish workflow triggers on git push of tags matching v* or via manual workflow_dispatch
The workflow runs bun install --frozen-lockfile, bun run typecheck, bun run test, then npm publish --provenance
npm publish runs prepublishOnly, which builds the web UI via bun run web:build
Before tagging a release, make sure the committed package.json version matches the intended git tag exactly
Preferred release flow: update package.json version, commit the release changes, create tag v<package.json version>, push the commit and tag, then verify the GitHub Actions publish and npm dist-tags
Do not create or push release tags from a dirty worktree with unrelated uncommitted changes; ask before including unrelated edits in a release

Read the full file on GitHub · 182 lines

Changes

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.

4d ago First seen · 182 lines · 3,617 tokens per session scan A 3d8dbf97962d

Subscribe to this mod's changes

motel AGENTS.md is an instructions file published in the GitHub repository kitlangton/motel (286 stars, last pushed yesterday), licensed MIT. It adds 3,617 tokens to every session, about $0.0181 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.

Git and workflow

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

motel AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Commands

Release Strategy

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

spec-kit AGENTS.md

codex AGENTS.md

langchain AGENTS.md

vscode oss-third-party-notices.instructions.md

next.js AGENTS.md