Borrowing it
Nothing to install: this file belongs to richardofortune/tyrekick. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/richardofortune/tyrekick/main/AGENTS.mdgit clone --depth 1 https://github.com/richardofortune/tyrekickWrote 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/richardofortune/tyrekick/agents-md)<a href="https://agentmods.dev/instructions/richardofortune/tyrekick/agents-md"><img src="https://agentmods.dev/badge/instructions/richardofortune/tyrekick/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.
<a href="https://agentmods.dev/instructions/richardofortune/tyrekick/agents-md"><img src="https://agentmods.dev/badge/instructions/richardofortune/tyrekick/agents-md.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 | $0.02767 | $0.02767 |
| Opus 5.5 | $0.01107 | $0.01107 |
| Sonnet 5.5 | $0.00553 | $0.00553 |
| Haiku 4.5 | $0.00277 | $0.00277 |
Grade A, and why
tyrekick 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.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tyrekick — instructions for coding agents
You are reading this because a human asked you to add feedback collection to a web project ("make this reviewable", "add tyrekick", "let people comment on this", "get feedback on this prototype"). This file tells you exactly what to do.
What Tyrekick is
A ~12 KB (gzipped) dependency-free script that adds a "Give feedback" button to any web page. Reviewers click a spot, type a comment, submit. The comment POSTs as structured JSON (element, visible text, heading, route, viewport, page errors) to a webhook the project owner controls. Later, you (or another agent) can pull the feedback back over MCP and act on it. Reviewers never need accounts.
Install (widget)
Have the
make-reviewableskill? (ships in this repo atskills/make-reviewable/, installable to~/.claude/skills/) — invoke it instead of following the steps below by hand. It runs this whole decision tree: destination choice by hosting risk, worker deploy with Discord mirroring, widget install, MCP registration, and drafts the ask message for reviewers.
-
Ask the human ONE question (skip if already configured in this project):
"Where should feedback go — a Discord webhook URL (easiest: Server Settings → Integrations → Webhooks → New Webhook → Copy URL), or a deployed Tyrekick worker URL?" Remember the answer for this project (e.g. note it in the project's CLAUDE.md or equivalent).
-
Run the installer (preferred — does everything below in one command):
npx tyrekick init --webhook THEIR_WEBHOOK_URL --yesIt finds the HTML entry file, injects the script tag (transport auto-detected from the URL, app version from the git SHA), sends a test comment, and prints the MCP setup command. Idempotent. Use
--file <path>if the HTML entry is unusual,--no-testto skip the test comment.Manual alternative — add the script tag before
</body>of the page/template (for SPAs: the root HTML file; for frameworks: the document/layout template):
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.
- 2mo ago First seen · 220 lines · 2,767 tokens per session scan A be4d55cebe61
tyrekick AGENTS.md is an instructions file published in the GitHub repository richardofortune/tyrekick (3 stars, last pushed 5d ago), licensed MIT. It adds 2,767 tokens to every session, about $0.0111 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.
tyrekick AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tyrekick AGENTS.mdrichardofortune/tyrekick | Instructions file | 3 | 5d ago | MIT | A | 2,767 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |