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/turnale-app/turnale/gemini-mdgit clone --depth 1 https://github.com/turnale-app/turnaleWrote 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/turnale-app/turnale/gemini-md)<a href="https://agentmods.dev/instructions/turnale-app/turnale/gemini-md"><img src="https://agentmods.dev/badge/instructions/turnale-app/turnale/gemini-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 | $0.00226 | $0.00226 |
| Opus 5 | $0.00113 | $0.00113 |
| Sonnet 5 | $0.00045 | $0.00045 |
| Haiku 4.5 | $0.00023 | $0.00023 |
Grade A, and why
turnale GEMINI.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 3d 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
Turnale — tournament organiser
You can run recreational racket-sport tournaments (tennis, padel, pickleball, badminton,
squash, table tennis) end to end through the turnale MCP server.
- Keep setup short: sport → players or headcount → time budget → social or competitive.
With only a headcount, create with
signup_open: trueso players add themselves via the page link; never invent placeholder names. - Never ask an open "which format?" question: call
suggest_format(orcreate_tournamentwithout a format) and relay the menu it returns as-is. - After creating, LEAD with the shareable page link; mention the organiser key (tk_…) once with the cannot-be-recovered warning.
- Scores are conversational ("Court 1: 9-7"); walkovers and retirements are recorded as
exactly that. Mutations support preview-then-confirm and
undo_last_change. get_briefingrecovers full context in a new session from just the organiser key.
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.
- 3d ago First seen · 16 lines · 226 tokens per session scan A eb96f7a8c616
turnale GEMINI.md is an instructions file published in the GitHub repository turnale-app/turnale (0 stars, last pushed 1mo ago), licensed MIT. It adds 226 tokens to every session, about $0.0011 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
skills AGENTS.md
AGENTS.md instructions for getanyapi-com/skills: This repository publishes customer-facing agent skills for the AnyAPI ecosystem. The authoritative wiring, contract invariants, impact classifier, repository gates, and rollout order live in the main repository's ECOSYSTEM.md.
horizon-shield GEMINI.md
Gemini CLI instructions for ogasurfproject-jpg/horizon-shield: You have the HORIZON SHIELD tools available. HORIZON SHIELD audits Japanese construction and renovation cost estimates against the open JCCDB dataset (95,403 line items) and returns fair-price references as tamper-evident, independently recomputable…
python-code-validator AGENTS.md
AGENTS.md instructions for jkanselaar/python-code-validator, covering python you write here gets checked, say what the code is for, before you write it, while you write, when something comes back wrong and before you present anything.
skills CLAUDE.md
Claude Code instructions for getanyapi-com/skills: Read and follow AGENTS.md before making changes. It points to the authoritative cross-repository ecosystem map and the required local gate.
python-code-validator GEMINI.md
Gemini CLI instructions for jkanselaar/python-code-validator, covering python you write here gets checked, say what the code is for, before you write it, while you write, when something comes back wrong and before you present anything.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).