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-buildgit 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-build)<a href="https://agentmods.dev/skills/tjdrhs90/flutter-flame-harness/flame-harness-build"><img src="https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-build/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-build"><img src="https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Privilege Escalation · line 198 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Rogue Agent · line 160 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 | $0.02477 |
| Opus 5 | $0.00019 | $0.01239 |
| Sonnet 5 | $0.00008 | $0.00495 |
| Haiku 4.5 | $0.00004 | $0.00248 |
Grade A, and why
flame-harness-build 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 10d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flame-harness-build
Phase 8 of the flutter-flame-harness pipeline. Bootstraps signing credentials into the generated game, generates fastlane config from the Task 3 templates, then builds and uploads a signed IPA to TestFlight and a signed AAB to the Play Store internal track.
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 including credentials_dir, ios, and android blocks; §2 for state.md; §6 for
log schemas; §7 for the build → screenshot transition and the status: running rule). Do not
redefine schemas here.
Prerequisites: An App Store Connect app record and a Google Play Console app must already exist (created once manually). The upload lanes will fail without them. Fastlane and Ruby must be installed on the developer's macOS machine (Xcode and the flutter CLI are assumed present).
Input — Read Inputs
Before any action, load:
docs/harness/config.md— extractapp_slug,bundle_id,app_name, andcredentials_dir(per protocol §1). Also readios.asc_key_idandandroid.key_alias.docs/harness/state.md— confirmnext_role: build(per protocol §2).
Derive the game root path: <projects-dir>/<app_slug>/.
Phase 1 — Credential Bootstrap
Copy signing credentials from the shared credentials_dir (per protocol §1 — skills must not
hard-code credential paths; always read credentials_dir from config.md) into the game's
platform directories.
iOS credentials
mkdir -p <game>/ios/fastlane/certs
cp <credentials_dir>/AuthKey_<asc-key-id>.p8 <game>/ios/fastlane/
The .p8 filename encodes the ASC key ID from config.md ios.asc_key_id. The certs/
directory holds the downloaded distribution certificate and provisioning profile (written by
fastlane certs).
Android credentials
mkdir -p <game>/android/fastlane
cp <credentials_dir>/play-store-key.json <game>/android/fastlane/
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.
- 10d ago First seen · 274 lines · 38 tokens per session scan A f6e527248a04
flame-harness-build is a skill published in the GitHub repository tjdrhs90/flutter-flame-harness (60 stars, last pushed 8d ago), licensed MIT. It adds 38 tokens to every session and 2,477 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
gamedev-team-release
Orchestrate the release team: coordinates release-manager, qa-lead, devops-engineer, and producer to execute a release from candidate to deployment.
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
changelog-automation
Git history'den otomatik changelog, semantic versioning, release notes, conventional commits.
git-workflow
Guided git workflows: prepare PRs, clean up branches, resolve merge conflicts, handle monorepo tags, squash-and-merge patterns. Use when asked to prepare a PR, clean branches, resolve conflicts, or tag a release.
github-release
Prepare and publish GitHub releases. Sanitizes code for public release (secrets scan, personal artifacts, LICENSE/README validation), creates version tags, and publishes via gh CLI. Trigger with 'release', 'publish', 'open source', 'prepare for release', 'create release', or 'github release'.
finalize
Finalize orphaned recordings - stop processes, compress, push to orphan branch. TRIGGERS - finalize recording, stop asciinema, orphaned recording.