flame-harness-evaluator

flame-harness-evaluator is a skill for Claude Code from tjdrhs90/flutter-flame-harness. It costs 41 tokens per session (6,103 once invoked), scanned A, original, MIT.

A quality-check step for a game that runs the app, watches the core gameplay, and decides whether it meets an agreed contract. Its strict mode also checks visual quality and edge cases, meaning unusual situations that may expose bugs.

In plain words
What is it for?
Use it as a pass-or-fail gate after building the game, with optional strict checks for quality and uncommon gameplay situations.
Why use it?
It tests the actual running game instead of trusting code review alone, and automatically rejects detected placeholder or stub implementations.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

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

Good fit Use it as a pass-or-fail gate after building the game, with optional strict checks for quality and uncommon gameplay situations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tjdrhs90/flutter-flame-harness/flame-harness-evaluator
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-evaluator
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-evaluator

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tjdrhs90/flutter-flame-harness/flame-harness-evaluator"><img src="https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-evaluator.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 6,103 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 12 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 165
    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.
  • high Privilege Escalation · line 168
    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 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.
  • medium Rogue Agent · line 145
    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 Excessive Agency · line 361
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 365
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 367
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 387
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 397
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 398
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 435
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.06103
Opus 5 $0.00020 $0.03052
Sonnet 5 $0.00008 $0.01221
Haiku 4.5 $0.00004 $0.00610

Measured 5d ago against content hash b00a26e39309, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

flame-harness-evaluator 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 5d 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.

skills/flame-harness-evaluator/SKILL.md · 453 lines

How it starts

The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.

flame-harness-evaluator

Phase 6 of the flutter-flame-harness pipeline. Skeptical QA gate that decides PASS or FAIL against the negotiated contract. Default mode runs the functional check (6.1) only; --strict adds quality scoring (6.2) and an agent-team edge-case sweep (6.3).

All file schemas (config.md, state.md, handoff/round-N-gen.md, feedback/round-N-qa.md, build-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; §3 for contract.md; §4 for handoff layout; §5 for feedback layout; §6 for log schemas; §7 for the evaluator → admob / evaluator → build / evaluator → generator transitions). Do not redefine schemas here.


Critical Rule

"Run the code, see the app, then judge." Never PASS on code review alone. Execute commands, launch the game on a simulator, play the core loop, capture and study screenshots. Stub detected = automatic FAIL, no exceptions.


Setup — Read Inputs

Before any check, load:

  1. docs/harness/state.md — extract current_round (integer ≥ 1) and confirm next_role: evaluator.
  2. docs/harness/config.md — extract app_slug, strict_mode (bool), max_rounds (int).
  3. docs/harness/contract.md — parse ## Mandatory Hard Gates and ## Functional Criteria. Confirm ## Status: AGREED is present; if missing, abort with: flame-harness-evaluator: contract not AGREED — run flame-harness-contract first.
  4. docs/harness/handoff/round-<N>-gen.md (where N = current_round) per protocol §4. If the file is missing, abort with: flame-harness-evaluator: handoff for round <N> not found — generator must run first.

6.1 Functional Check (default — always runs)

Run every step in order. A failure on any Mandatory Hard Gate from contract.md is an immediate FAIL — do not continue checking remaining criteria.

Step 1 — Static analysis

cd <projects-dir>/<app_slug>
flutter analyze

Read the full file on GitHub · 453 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. 5d ago Changed · +6 lines b00a26e39309
  2. 9d ago First seen · 447 lines · 41 tokens per session scan A abf6d46d865d

Subscribe to this mod's changes

flame-harness-evaluator 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 6,103 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.

Related

Other skills, from other repositories

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

gamedev-team-qa

Orchestrate the QA team through a full testing cycle. Coordinates qa-lead (strategy + test plan) and qa-tester (test case writing + bug reporting) to produce a complete QA package for a sprint or feature. Covers: test plan generation, test case writing, smoke check gate, manual QA execution, and sign-off report.

FluxonLab/Skillry · 75 tokens

smoke-check

Run the critical path smoke test gate before QA hand-off. Executes the automated test suite, verifies core functionality, and produces a PASS/FAIL report. Run after a sprint's stories are implemented and before manual QA begins. A failed smoke check means the build is not ready for QA.

Donchitos/Claude-Code-Game-Studios · 61 tokens

regression-suite

Map test coverage to GDD critical paths, identify fixed bugs without regression tests, flag coverage drift from new features, and maintain tests/regression-suite.md. Run after implementing a bug fix or before a release gate.

Donchitos/Claude-Code-Game-Studios · 47 tokens

soak-test

Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

Donchitos/Claude-Code-Game-Studios · 54 tokens

playtest-report

Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

Donchitos/Claude-Code-Game-Studios · 35 tokens