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 instructions/tickadoo/tickadoo-mcp/agents-mdgit clone --depth 1 https://github.com/tickadoo/tickadoo-mcpWrote 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/instructions/tickadoo/tickadoo-mcp/agents-md)<a href="https://agentmods.dev/instructions/tickadoo/tickadoo-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/tickadoo/tickadoo-mcp/agents-md.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 | $0.02393 | $0.02393 |
| Opus 5 | $0.01196 | $0.01196 |
| Sonnet 5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00239 | $0.00239 |
Grade A, and why
tickadoo-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 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Shared instructions for AI coding agents
This file is automatically read by Codex CLI (and some other AI coding tools) at task start. It's the shared ruleset for every AI agent that does work on this repo: Claude chats, Claude Code sessions, and Codex tasks.
This repo is @tickadoo/mcp-server — the npm distribution of the public tickadoo MCP server (23 tools over 13,090 products in 681 cities). Since v2.0.0 it is a thin remote bridge that proxies to the canonical remote server at https://mcp.tickadoo.com/mcp. The remote server and the embeddable widget bundle live in HowardOS (github.com/tickadoo/howard), which is canonical; this repo ships only the stdio bridge.
Issue tracking: GitHub Issues (Linear frozen 2026-08-18)
New work is a GitHub issue #NNNN in this repo, on the shared Project
board. Do not open Linear issues.
Legacy GRO- / BAC- / TIC- IDs are read-only historical references and
resolve to tickadoo/linear-archive,
never to a GitHub issue number. Grep that repo rather than calling an API. All
three namespaces are frozen; never mint a new one.
Canonical policy lives in tickadoo/howard:
AGENTS.md → "Issue tracking"
and docs/operations/linear-to-github-issues.md.
Before you do anything
- Pull first: run
git pull --rebase origin mainat task start. Codex worktrees (see.claude/worktrees/) may be stale clones; without a pull you may be reading an old version of this file orCLAUDE.mdthat predates recent changes. - Check Hive before editing: use the
claude_platformtools to inspect presence, recent activity, inboxes, reservations, and blockers fortickadoo/tickadoo-mcp. Reserve the paths you intend to edit and release them after handoff or completion. If Hive is unavailable, presence is unknown: inspect open pull requests, use a narrow isolated branch, and ask the human dispatcher when material overlap remains possible. Never use Slack as a coordination input. - Read
CLAUDE.md(if present — a minimal one lives at repo root). Also read the HowardOS repoCLAUDE.md(github.com/tickadoo/howard→CLAUDE.md) for the broader tickadoo project context (supplier pipeline, booking flows, content rules, team). Anything in the HowardOSCLAUDE.mdthat applies to the MCP server applies here too. - Before each push:
git pull --rebase origin mainagain. Multiple agents push tomainconcurrently — racing is the default, not the exception.
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 · 152 lines · 2,393 tokens per session scan A 1706b6950721
tickadoo-mcp AGENTS.md is an instructions file published in the GitHub repository tickadoo/tickadoo-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 2,393 tokens to every session, about $0.0120 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 instructions, from other repositories
cli AGENTS.md
AGENTS.md instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.
notfair-plugin AGENTS.md
AGENTS.md instructions for nowork-studio/notfair-plugin, covering notfair — skill resolver for ai agents, how to use this file, seo, paid ads and analytics.
Agentkey AGENTS.md
Instructions for chainbase-labs/Agentkey, covering agents.md, what this repo is, directory structure, key commands and test a local edit against every detected agent.
domscribe CLAUDE.md
Instructions for patchorbit/domscribe, covering claude.md, what is domscribe?, how to work on this codebase, commands and install dependencies (pnpm, not npm).
adeu GEMINI.md
Gemini CLI instructions for dealfluence/adeu, covering adeu — native track changes for ai, available tools, readdocx, processdocumentbatch and applytextrevision.
bookstack-mcp CLAUDE.md
Instructions for ttpears/bookstack-mcp, covering claude.md, project overview, build & development commands, architecture and configuration.