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 skills add richardofortune/tyrekick --skill make-reviewablegit 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/skills/richardofortune/tyrekick/make-reviewable)<a href="https://agentmods.dev/skills/richardofortune/tyrekick/make-reviewable"><img src="https://agentmods.dev/badge/skills/richardofortune/tyrekick/make-reviewable/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/skills/richardofortune/tyrekick/make-reviewable"><img src="https://agentmods.dev/badge/skills/richardofortune/tyrekick/make-reviewable.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 | $0.00162 | $0.03859 |
| Opus 5 | $0.00081 | $0.01929 |
| Sonnet 5 | $0.00032 | $0.00772 |
| Haiku 4.5 | $0.00016 | $0.00386 |
Grade B, and why
make-reviewable scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
repo — `~/.tyrekick/cloudflare.env`, `chmod 600` — so it stays out of the Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST https://tyrekick-<slug>.<acct>.workers.dev/feedback \ How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
make-reviewable
Goal: from "make this reviewable, ask Dave to check the checkout" to a live, instrumented page plus a ready-to-paste ask message, in one pass. The human should never have to know what a webhook, worker, or token is.
1. Gather facts (ask at most ONE question)
Check before asking anything:
- Already installed? Grep the HTML entry for
data-webhookortyrekick. If present, skip to step 6 (the ask) — never redirect an existing destination. One check first: runnpx tyrekick status. If the Review row says closed, the endpoint refuses new comments, so runnpx tyrekick reopen --days 14before you send anyone the link (same URL, same store). See step 5. - Previous decisions? Check the project's CLAUDE.md (or equivalent) for a recorded Tyrekick destination / project slug. Reuse them.
- Does the app even have a home? The loop needs the page to load from an
http(s) origin — a
file://artifact, an emailed HTML file, or a script-generated page with no host CANNOT send feedback out or get receipts back. Classify:- hosted — already at an http(s) URL (deployed, or a dev server reviewers can reach). Note the URL; no hosting needed.
- unhosted — a static build, a single generated HTML file, or anything
only openable via
file://. It has no origin → give it one in step 2.
- Where does this deploy? Infer from the repo:
netlify.toml,vercel.json,wrangler.toml,CNAME, gh-pages workflows, or the user's own words. Classify:- private — localhost, LAN, a tunnel the user just opened
- public — any preview/static host URL or real domain
- Project slug: kebab-case of the folder name unless one is recorded. Chosen ONCE, never derived from the page title, never changed.
- App version:
git rev-parse --short HEAD(fallbackv0.1).
If no destination is recorded and you cannot infer hosting, ask the one question: "Where will this be hosted (just locally / a public URL), and do you have a Discord channel you'd like feedback mirrored to?"
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 Changed · +63 lines scan A → B c2f2fa7418ba
- 9d ago First seen · 235 lines · 162 tokens per session scan A d88124ebe968
make-reviewable is a skill published in the GitHub repository richardofortune/tyrekick (2 stars, last pushed today), licensed MIT. It adds 162 tokens to every session and 3,859 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.