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 tjdrhs90/flutter-flame-harness --skill flame-harness-screenshotgit clone --depth 1 https://github.com/tjdrhs90/flutter-flame-harnessWrote 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/tjdrhs90/flutter-flame-harness/flame-harness-screenshot)<a href="https://agentmods.dev/skills/tjdrhs90/flutter-flame-harness/flame-harness-screenshot"><img src="https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-screenshot/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/tjdrhs90/flutter-flame-harness/flame-harness-screenshot"><img src="https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-screenshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 276 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00037 | $0.03951 |
| Opus 5 | $0.00018 | $0.01975 |
| Sonnet 5 | $0.00007 | $0.00790 |
| Haiku 4.5 | $0.00004 | $0.00395 |
Grade A, and why
flame-harness-screenshot 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 11d 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 — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flame-harness-screenshot
Phase 9 of the flutter-flame-harness pipeline. Captures KO and EN store screenshots by driving the
game's integration_test harness on the required device sizes (ads hidden), fills ASO metadata
(keywords, localized titles, descriptions), and uploads the screenshots via fastlane.
All file schemas (config.md, state.md, pipeline-log.md) and the phase transition table are
defined in docs/harness-protocol.md — that document is the single source of truth (§1 for
config.md and credentials_dir; §2 for state.md; §6 for log schemas; §7 for the
screenshot → submit transition and the status: running rule). Do not redefine schemas here.
Prerequisites: The game has been built and uploaded (Phase 8 flame-harness-build). The iOS
simulator is a 6.7" iPhone model and the Android emulator is a phone-sized device. flutter drive
and fastlane must be installed on the developer's macOS machine.
Input — Read Inputs
Before any action, load:
docs/harness/config.md— extractapp_slug,bundle_id,app_name, anddefault_language(per protocol §1).docs/harness/state.md— confirmnext_role: screenshot(per protocol §2).
Derive the game root path: <projects-dir>/<app_slug>/.
Phase 1 — Harness Setup
Copy the integration_test template
Copy templates/screenshots_test.dart.template into the game's integration_test/ directory:
mkdir -p <game>/integration_test
cp templates/screenshots_test.dart.template \
<game>/integration_test/screenshots_test.dart
Adapt the TODO markers
Open <game>/integration_test/screenshots_test.dart and replace every
// TODO(generator): comment block with the game's real screen-driving code:
- Replace
<__APP_SLUG__>in the import with the actual package name (fromconfig.mdapp_slug, converting hyphens to underscores). - Seed mock SharedPreferences / Hive / Isar data to skip first-run tutorials and show a representative UI state (high score, coins, unlocked skins).
- Wire the locale controller to force the locale to the
SCREENSHOT_LOCALEdart-define value so screenshots are language-deterministic regardless of the simulator's system locale. - Replace the placeholder screen list with the game's actual key screens (home, gameplay, game-over/results, optional secondary screen), keeping zero-padded two-digit name prefixes so fastlane and App Store Connect receive them in order.
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.
- 11d ago First seen · 416 lines · 37 tokens per session scan A 7d5841d664ab
flame-harness-screenshot is a skill published in the GitHub repository tjdrhs90/flutter-flame-harness (60 stars, last pushed 9d ago), licensed MIT. It adds 37 tokens to every session and 3,951 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
implementation-guide
Generates detailed implementation guide with pseudo-code and step-by-step development instructions. Creates IMPLEMENTATIONGUIDE.md from PRD, Architecture, and UX specs. Use when creating development roadmap.
architecture-spec
Generates technical architecture specification from PRD. Covers architecture pattern, tech stack, data models, and app structure. Use when creating ARCHITECTURE.md or designing system architecture.
foundation-models
On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.
liquid-glass
Implement Liquid Glass design using .glassEffect() API for iOS/macOS 26+. Covers SwiftUI, AppKit, UIKit, and WidgetKit. Use when creating modern glass-based UI effects.
beta-testing
Beta testing strategy for iOS/macOS apps. Covers TestFlight program setup, beta tester recruitment, feedback collection methodology, user interviews, signal-vs-noise interpretation, and go/no-go launch readiness decisions. Use when planning a beta, setting up TestFlight, collecting user feedback, or deciding if ready…
app-intents
App Intents for Siri, Shortcuts, Spotlight, and Apple Intelligence integration including intent modes, interactive snippets, visual intelligence, and entity indexing. Use when implementing Siri integration, App Shortcuts, or Spotlight indexing.