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 makifbaysal/tasktrooper --skill game-visual-self-reviewgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/game-visual-self-review)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/game-visual-self-review"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/game-visual-self-review/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/makifbaysal/tasktrooper/game-visual-self-review"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/game-visual-self-review.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 | $0.00074 | $0.02068 |
| Opus 5.5 | $0.00030 | $0.00827 |
| Sonnet 5.5 | $0.00015 | $0.00414 |
| Haiku 4.5 | $0.00007 | $0.00207 |
Grade A, and why
game-visual-self-review 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 4d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Visual Self-Review
Overview
A green test suite says the rules are right in isolation. It does not say the sprite loaded, the camera points at the action, the HUD shows the new value, or the scene is not black. Look at the change running before you hand it off — and when this machine cannot render the game, say exactly that instead of implying you saw it.
Core principle: Default assumption: the change is NOT done until you have seen it rendered. A still frame proves presence and layout; timing and feel are proven by tests at fixed deltas and frame-time numbers.
The render paths
Name the one you used in the closing message:
- browser — a web game in the shared browser.
- engine capture — a frame written to PNG by the engine (headless or offscreen), opened over loopback.
- not observable here — no editor, GPU, display or licence; say which, and comment it on the card.
Web games — the matrix and the tool calls
Matrix: desktop {device: "desktop"} (1440×900) and phone {device: "mobile", width: 360}; add landscape {device: "mobile", width: 844, height: 390} when the game targets phones.
- Dev server detached, as the main prompt describes; read the port from the log.
browser_set_viewport→browser_navigateto the game with the repository's debug parameters (?seed=42&scene=Level2) so it opens on the changed content deterministically.browser_wait_forthecanvas(or the DOM overlay that proves boot finished),browser_clickthrough DOM menus.browser_screenshotwith NOwidth— passingwidthre-emulates and discards the viewport you set.- Read the
browser_set_viewportreport: the canvas must not overflow; it fits or letterboxes.
The browser tools cannot press keys or read the console. For both, run a seeded Playwright smoke script with run_terminal — use the repository's Playwright setup if it has one (web-game-performance-and-testing), otherwise a throwaway script in /tmp/tt-<task key>/ when playwright is already installed:
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.
- 4d ago First seen · 134 lines · 74 tokens per session scan A 0553b7a54e1c
game-visual-self-review is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 74 tokens to every session and 2,068 once invoked, about $0.0003 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 2026-10-09.
Other skills, from other repositories
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
agent-benchmark-suite
Agent skill for benchmark-suite - invoke with $agent-benchmark-suite.
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
agent-production-validator
Agent skill for production-validator - invoke with $agent-production-validator.
agent-tdd-london-swarm
Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm.
agent-tester
Agent skill for tester - invoke with $agent-tester.