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-plangit 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-plan)<a href="https://agentmods.dev/skills/tjdrhs90/flutter-flame-harness/flame-harness-plan"><img src="https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-plan/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-plan"><img src="https://agentmods.dev/badge/skills/tjdrhs90/flutter-flame-harness/flame-harness-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.03030 |
| Opus 5.5 | $0.00021 | $0.01212 |
| Sonnet 5.5 | $0.00011 | $0.00606 |
| Haiku 4.5 | $0.00005 | $0.00303 |
Grade A, and why
flame-harness-plan 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 2mo 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
flame-harness-plan
Phase 2 of the flutter-flame-harness pipeline. Reads the research spec and config.md, then
produces a comprehensive game PRD in the project's default_language, maps the lib/ directory structure, assigns the app
identity (app_name, app_slug, bundle_id), and advances the pipeline state to design.
All file schemas (config.md, state.md, pipeline-log.md) are defined in
docs/harness-protocol.md — refer to that document as the single source of truth. Do not
redefine schemas here.
Input
1. Read docs/harness/config.md
Extract:
| Key | Use |
|---|---|
app_idea |
Refined concept tagline written by the research phase |
app_name |
Display name (may be blank — set it here if so) |
app_slug |
Kebab-case identifier (may be blank — derive it here if so) |
bundle_id |
App bundle ID (may be blank — set it here) |
default_language |
The user's conversation language (set by the orchestrator); the PRD and all copy are written in it |
If config.md does not exist, abort with:
flame-harness-plan: docs/harness/config.md not found — run the orchestrator to bootstrap first.
2. Read the latest research spec
Find the most recent file matching docs/harness/specs/*-research.md (sort by filename
descending, take the first). If no spec file exists, abort with:
flame-harness-plan: no research spec found in docs/harness/specs/ — run flame-harness-research first.
Extract from the spec:
- Chosen concept — title, tagline, core mechanic, differentiator
- Monetisation hook — AdMob integration point (interstitial / rewarded / banner)
- Clone-avoidance verdict — confirm it is SAFE before proceeding
Identity assignment
Derive and assign the app identity before writing the PRD so that the PRD can reference the final values.
app_name
Use the working title from the research spec as the display name. Capitalise each word. Example:
"space hop" → "Space Hop".
app_slug
The app_slug is a kebab-case identifier derived from app_name:
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.
- 2mo ago First seen · 337 lines · 53 tokens per session scan A b082880c77ca
flame-harness-plan is a skill published in the GitHub repository tjdrhs90/flutter-flame-harness (61 stars, last pushed 10d ago), licensed MIT. It adds 53 tokens to every session and 3,030 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.
flame-harness-plan compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flame-harness-plantjdrhs90/flutter-flame-harness | Skill | 61 | 10d ago | MIT | A | 53 | Claude Code |
| variable-rewardsrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 45 | Claude Code |
| forge-gameForgeyClap/claude-forge | Skill | 2 | 1mo ago | MIT | A | 0 | Claude Code |
| minecraft-modpack-serverStarryCod/cogitum | Skill | 12 | 5mo ago | MIT | B | 19 | Claude Code, Codex |
| release-checklistDonchitos/Claude-Code-Game-Studios | Skill | 36k | 19d ago | MIT | A | 20 | Claude Code |
| day-one-patchDonchitos/Claude-Code-Game-Studios | Skill | 36k | 19d ago | MIT | A | 29 | Claude Code |
| quick-designDonchitos/Claude-Code-Game-Studios | Skill | 36k | 19d ago | MIT | A | 27 | Claude Code |