agentmods.dev

flame-harness-generator

flame-harness-generator is a skill for Claude Code from tjdrhs90/flutter-flame-harness. It costs 41 tokens per session (9,335 once invoked), scanned C, original, MIT.

A staged build workflow for a Flame game, where Flame is a game framework for Flutter apps. It builds the game in three phases and checks the code and tests after each phase.

In plain words
What is it for?
It is for implementing a configured Flame game through its core loop, systems and components, then user interface and content.
Why use it?
It catches analysis errors and failing tests before later parts of the game are built, and uses earlier evaluator feedback on later rounds.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the flutter-flame-harness plugin — 14 skills shipped together

not rated 60repo +1 8d ago C scan 41 tokens original MIT

Good fit It is for implementing a configured Flame game through its core loop, systems and components, then user interface and content.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tjdrhs90/flutter-flame-harness/flame-harness-generator
View source ↗ tjdrhs90/flutter-flame-harness
Install

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.

Any agent
npx skills add tjdrhs90/flutter-flame-harness --skill flame-harness-generator
Clone the repo
git clone --depth 1 https://github.com/tjdrhs90/flutter-flame-harness

Made for: Claude Code.

Or install flutter-flame-harness, the plugin that ships this one along with the rest of its 14 skills.

Wrote 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.

agentmods badge for flame-harness-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-generator/github.svg)](https://agentmods.dev/skills/tjdrhs90/flutter-flame-harness/flame-harness-generator)
Your own site
<a href="https://agentmods.dev/skills/tjdrhs90/flutter-flame-harness/flame-harness-generator"><img src="https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-generator/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.

agentmods 80×15 button for flame-harness-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/tjdrhs90/flutter-flame-harness/flame-harness-generator"><img src="https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,335 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.09335
Opus 5 $0.00020 $0.04667
Sonnet 5 $0.00008 $0.01867
Haiku 4.5 $0.00004 $0.00933

Measured 10d ago against content hash 50d67850305d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

flame-harness-generator scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

of hard-failing. (If the user passed `--clean`, `rm -rf "$GAME"` first, then create fresh.)
skills/flame-harness-generator/SKILL.md · 835 lines

How it starts

The opening of the file, as written. The whole thing — 835 lines — stays where its author put it; the contents beside it link to each section on GitHub.

flame-harness-generator

Phase 5 of the flutter-flame-harness pipeline. Builds the Flame game in three gated sub-phases (5a → 5b → 5c). Each sub-phase ends with a HARD GATE (flutter analyze zero issues + flutter test all pass) before the next sub-phase begins. On round N > 1, reads the previous evaluator feedback and fixes only the listed failures.

All file schemas (config.md, state.md, handoff/round-N-gen.md, feedback/round-N-qa.md) and the phase transition table are defined in docs/harness-protocol.md — that document is the single source of truth (§2 for state.md schema; §4 for handoff layout; §5 for feedback layout; §7 for the generator → evaluator transition). Do not redefine schemas here.

Round Handling and Feedback Intake

Determine current round

Read docs/harness/state.md. Extract current_round (integer, ≥ 1).

Round 1 — build from scratch

When current_round is 1:

  1. Read docs/harness/config.md (extract app_slug, app_name, bundle_id, default_language, skip_admob).
  2. Read the latest PRD (docs/harness/plans/*-prd.md, sort descending, take first).
  3. Read the latest design doc (docs/harness/plans/*-design.md, sort descending, take first).
  4. Read docs/harness/contract.md. Confirm ## Status: AGREED is present; abort with flame-harness-generator: contract not AGREED — run flame-harness-contract first if missing.
  5. Read checkpoint from state.md (see docs/harness-protocol.md §2). Re-entry: if a prior run crashed/paused mid-phase, skip every sub-phase ≤ checkpoint (its HARD GATE already passed and its output exists) and resume at the next one — e.g. checkpoint: 5a → start at 5b. If checkpoint is "", start at 5a. This makes the generator safe to re-run without redoing (or colliding with) completed work.

Round N > 1 — fix only listed failures (feedback intake)

When current_round is greater than 1:

  1. Read docs/harness/feedback/round-<N-1>-qa.md (per docs/harness-protocol.md §5 layout).
  2. Parse the ## Failed Criteria section to extract each failing criterion and its prescribed fix.
  3. Do NOT redesign or refactor areas that were not listed as failures. Make only the minimum changes required to satisfy the listed fixes.
  4. If docs/harness/feedback/round-<N-1>-qa.md does not exist, abort with: flame-harness-generator: feedback file for round <N-1> not found — cannot determine fixes.
  5. Apply each fix, then run the HARD GATE for the affected sub-phase before writing the handoff.

Read the full file on GitHub · 835 lines

Changes

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.

  1. 10d ago First seen · 835 lines · 41 tokens per session scan C 50d67850305d

Subscribe to this mod's changes

flame-harness-generator is a skill published in the GitHub repository tjdrhs90/flutter-flame-harness (60 stars, last pushed 8d ago), licensed MIT. It adds 41 tokens to every session and 9,335 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodeGame developmentagenticai-agentanthropicapp-storeautomation
Related

Other skills, from other repositories

achievements

Steam-style achievement system with XP, levels, streaks, and skill trees. Gamifies the development workflow. 25 achievements across 5 categories.

vibeeval/vibecosystem · 33 tokens

variable-rewards

Generates a variable reward system with randomized rewards, daily bonuses, mystery box mechanics, and ethical engagement caps. Use when user wants daily spins, mystery boxes, random rewards, or gamification reward systems.

rshankras/claude-code-apple-skills · 45 tokens

game-development

Game development with Unity, Unreal Engine, and Godot. Use when building games, implementing game mechanics, physics, AI, or working with game engines.

travisjneuman/.claude · 34 tokens

ar-vr-xr

AR/VR/XR development with Unity XR, WebXR, ARKit, ARCore, Meta Quest SDK, and spatial computing. Use when building augmented reality, virtual reality, mixed reality applications, or spatial experiences.

travisjneuman/.claude · 50 tokens

fabrik-validate

Use when operating as the Fabrik Validate stage agent. This skill guides final validation of an implementation, verifying requirements are met, tests pass, and the PR is ready to merge.

handarbeit/fabrik · 36 tokens

fabrik-review

Use when operating as the Fabrik Review stage agent. This skill guides code review of an implementation, finding and fixing issues, and ensuring the PR is ready for human review.

handarbeit/fabrik · 35 tokens