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-submitgit 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-submit)<a href="https://agentmods.dev/skills/tjdrhs90/flutter-flame-harness/flame-harness-submit"><img src="https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-submit/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-submit"><img src="https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-submit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Rogue Agent · line 140 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 143 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00038 | $0.04128 |
| Opus 5.5 | $0.00015 | $0.01651 |
| Sonnet 5.5 | $0.00008 | $0.00826 |
| Haiku 4.5 | $0.00004 | $0.00413 |
Grade A, and why
flame-harness-submit 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 1mo 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flame-harness-submit
Phase 10 of the flutter-flame-harness pipeline. Uploads store text metadata and app categories via fastlane for both iOS and Android, then pauses the pipeline with exact manual steps for the final review submission / production promotion (see Boundary below for what is genuinely manual and what is a deliberate checkpoint).
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; §2 for state.md keys and pause_reason values; §6 for pipeline-log.md schema;
§7 for the submit → metadata-done → paused transition and the (paused) → resume → retro
transition). Do not redefine schemas here.
Boundary: Text metadata upload is automated. The final "Submit for Review" on iOS and the "Promote to production" action on Android are manual in this pipeline — deliberately, so a human sees the assembled listing once before it goes out, and because the Play questionnaires (Content Rating, Data Safety, Target Audience) have no API.
Note the iOS half is automatable if you want it: reviewSubmissions will submit a version
end-to-end (see iOS submission over the API below). What is genuinely not automatable is the
Play side and the age-rating questionnaire. Keep the pause unless you have a reason not to — the
review is the point of it.
Prerequisites: Phase 9 (flame-harness-screenshot) completed; screenshots and ASO metadata
already uploaded; state.md shows next_role: submit.
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: submit(per protocol §2).
Derive the game project root for <app_slug> from config.md / the harness working directory (the games live under the same parent as the harness, e.g. …/AndroidStudioProjects/<app_slug>/).
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.
- 1mo ago First seen · 311 lines · 38 tokens per session scan A c08c8db01f39
flame-harness-submit is a skill published in the GitHub repository tjdrhs90/flutter-flame-harness (61 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 4,128 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
testflight-release
Ship a new TestFlight build of the iOS companion (TermioMobile) — resolve the next build number against App Store Connect, archive, sign, export, upload, write the What to Test notes, and distribute. Invoke when the user says 'ship a testflight build', 'update testflight', 'upload to testflight', 'new beta build'…
suede-play-release
Suede AI Google Play delivery skill: ship an Android release from the agent interface and prove what is live. Preflight the publishing credential with a real Play API call, upload an AAB to a testing track, promote that exact versionCode, stage or complete a rollout, write per-locale release notes, and read back…
release-plugin
Cut a cairn plugin release for a given MAJOR.MINOR.PATCH version, running every pre-flight and version gate before anything is changed or published.
rn-harness-submit
Phase 10 — Submit to App Store Connect (iOS) and Google Play (Android). iOS fully automated, Android pauses for manual steps.
ios-app-store-release
Use when preparing, archiving, uploading, or submitting iOS apps through App Store Connect. Covers xcodebuild archive/export, Fastlane deliver, altool/transporter fallback, TestFlight, review submission, App Privacy, export compliance, release safety, and slash commands such as /ios-release and /ios-grade.
apple-app-delivery
A release workflow for iPhone and iPad apps that uses Apple's command-line tools and App Store Connect, Apple's service for managing app releases.