yeehaw-mcp: Instructions file for Codex

AGENTS.md

yeehaw-mcp AGENTS.md is an instructions file for Codex, OpenCode from capitalthought/yeehaw-mcp. It costs 704 tokens per session, scanned A, original, MIT.

Instructions for using Yeehaw, a service that finds events happening in Austin. They define which tools to call, their arguments, and their limits.

In plain words
What is it for?
Use them to find Austin events, check the service’s source health, or fetch one event by its identifier.
Why use it?
They help the agent ask the event service correctly and avoid claiming more coverage or freshness than it provides.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is capitalthought/yeehaw-mcp's own configuration. It tells Codex and OpenCode how to work on yeehaw-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything yeehaw-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to capitalthought/yeehaw-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/capitalthought/yeehaw-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/capitalthought/yeehaw-mcp

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.

agentmods badge for yeehaw-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/capitalthought/yeehaw-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/capitalthought/yeehaw-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/capitalthought/yeehaw-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/capitalthought/yeehaw-mcp/agents-md/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.

agentmods 80×15 button for yeehaw-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/capitalthought/yeehaw-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/capitalthought/yeehaw-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 704 This file is loaded in full into every session.
When invoked 704 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00704 $0.00704
Opus 5.5 $0.00282 $0.00282
Sonnet 5.5 $0.00141 $0.00141
Haiku 4.5 $0.00070 $0.00070

Measured 2mo ago against content hash 9e10278b32dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yeehaw-mcp 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 2mo 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 · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Yeehaw usage contract

Rules an agent can't infer from the schema. Endpoint: https://yeehaw.bot/mcp (JSON-RPC over HTTP POST). No auth.

When to call what

  • find_events — the workhorse. Use for any "what's happening / what's on / things to do" question about Austin.
  • overview — call FIRST when you need to trust freshness, or to answer "how much coverage is there?" / "is a source down?". Returns counts + per-source last-ingest + health. No arguments.

find_events arguments

  • date_range (required unless id is set): one of today, tomorrow, this_weekend, next_7_days, next_30_days.
  • id (optional): fetch exactly one event by its id. When set, date_range and all other filters are ignored. Use it to render/cite a specific event.
  • query (optional): free-text; matches event title OR venue name. Substrings are escaped (no LIKE-wildcard injection).
  • category (optional): one of music, tech, comedy, arts, film, food, sports, festival, family, community, civic.
  • neighborhood (optional): east-austin, downtown, south-congress, rainey, the-domain, north-loop, east-sixth, the-drag (shorthands like east, soco, domain, rainey resolve too).
  • price_max (optional): 0 means known-free only (unpriced events excluded — "free" is an affirmative claim). >0 includes unpriced events; the human summary states how many weren't price-filtered.
  • limit (optional): default is sensible; results come back ranked then chronological.

What you get back

Each event: id, title, when (ISO 8601), venue, category, price_min/price_max (often null), url (deep link to the source), image, lat/lng, source, confidence. There is also a top-level human one-line summary you can surface verbatim.

Honest caveats (don't over-promise to your user)

  • Prices are sparse. Most events have null prices (upstream feeds don't expose them). Don't claim "free" unless price_min === 0. Link to url for ticketing.
  • Cite the source. Every event has a source + url — attribute it; don't present Yeehaw data as your own knowledge.
  • Austin only (V1). For other cities, say so.
  • ask_yeehaw is not live yet — only find_events and overview are advertised in tools/list. Don't call tools that aren't listed.

Read the full file on GitHub · 33 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.

  1. 2mo ago First seen · 33 lines · 704 tokens per session scan A 9e10278b32dc

Subscribe to this mod's changes

yeehaw-mcp AGENTS.md is an instructions file published in the GitHub repository capitalthought/yeehaw-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 704 tokens to every session, about $0.0028 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.

Related

yeehaw-mcp AGENTS.md compared with instructions from other repositories

yeehaw-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
yeehaw-mcp AGENTS.mdcapitalthought/yeehaw-mcpInstructions file05mo agoMITA704Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode