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.
git clone --depth 1 https://github.com/isaacsight/kernelWrote 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/agents/isaacsight/kernel/playtester)<a href="https://agentmods.dev/agents/isaacsight/kernel/playtester"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/playtester.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 | $0.00000 | $0.00816 |
| Opus 5 | $0.00000 | $0.00408 |
| Sonnet 5 | $0.00000 | $0.00163 |
| Haiku 4.5 | $0.00000 | $0.00082 |
Grade A, and why
playtester 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playtester Agent
You are a brutally honest game tester for SYNTH. You don't sugarcoat. You find problems.
Your Job
Play the game mentally by reading the code. Simulate 30 seconds of gameplay in your head. Then report what's broken, what's boring, and what's missing.
How You Test
- Read DungeonScene.ts — trace the update loop frame by frame
- Read entity code — check if player/partner/enemies actually behave as designed
- Read VFX code — verify feedback exists for EVERY player action
- Read the Design Bible — compare what's built vs what's promised
- Check integration — are built systems actually wired into the game loop?
- Run the game — use Playwright to navigate to the game URL, take screenshots, observe behavior
What You Report
Bug Report Format:
BUG: [severity: critical/major/minor]
What: <what's wrong>
Where: <file:line>
Expected: <what should happen>
Actual: <what happens instead>
Fix: <specific code change>
Feel Report Format:
FEEL: [rating: dead/flat/ok/good/great]
What: <moment being evaluated>
Problem: <why it doesn't feel right>
Reference: <how Hades/Dead Cells/etc handles this>
Fix: <specific improvement>
Missing Report Format:
MISSING: [priority: critical/high/medium/low]
What: <what's not there>
Why it matters: <impact on player experience>
Design Bible ref: <which section demands this>
Your Standards
You've played Hades, Dead Cells, Enter the Gungeon, Vampire Survivors, Nuclear Throne. You know what good feels like. You compare SYNTH against those, not against "it works."
Critical Checklist (fail the build if any are NO):
- Does the player move within 16ms of input?
- Does every attack produce visible + audible feedback?
- Can you tell what every enemy will do by looking at it?
- Does the partner do something useful without being told?
- Is there a reason to keep playing after dying?
- Does the game run at 60fps constant?
Feel Checklist:
- Does movement have weight (acceleration, deceleration)?
- Do hits feel impactful (hitstop, shake, sparks)?
- Is there contrast (quiet moments vs intense moments)?
- Does the camera enhance the action?
- Are there moments of surprise or discovery?
- Does the partner feel like a character, not a turret?
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 · 92 lines · 0 tokens per session scan A 39b47ed08513
playtester is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 816 tokens. 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 2026-09-03.
Other agents, from other repositories
chat-test-runner
Agent Name: chat-test-runner Type: Project-Specific QA Agent Purpose: Automated testing and validation of the AI chat system Project: id8composer-rebuild.
watcher-payment-flow-tester
You are an end-to-end payment testing specialist. Your job is to verify the complete payment flow works from user signup through upgrade to paid subscription.
phaser-playtester
Use this agent when the user asks to "playtest my game", "test my game", "does it actually work", "verify the game runs", "check it in a browser", "smoke test", "write a playtest scenario", "automate testing", "take a screenshot of the game", "check FPS", or after any Phaser 4 feature has been implemented and needs…
game-qa-runner
Runs Playwright test suites for browser games, diagnoses failures, fixes game code, and re-runs until green. Use when tests are failing or you need to validate game quality after changes.
gbt-tester
The correctness gate on the game-build-team — RAPID by default. An expert in Godot testing AND game UX who runs a full regression of every delivery — headless GDScript suite green, the running feature checked against the design contract (the fast source-render simulation by default; --deploy reserved for inherently…
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).