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 agentmods add agents/melons/melons-agents/game-narrative-designergit clone --depth 1 https://github.com/MelonS/MelonS-AgentsWrote 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/agents/melons/melons-agents/game-narrative-designer)<a href="https://agentmods.dev/agents/melons/melons-agents/game-narrative-designer"><img src="https://agentmods.dev/badge/agents/melons/melons-agents/game-narrative-designer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00058 | $0.00559 |
| Opus 5 | $0.00029 | $0.00280 |
| Sonnet 5 | $0.00012 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
game-narrative-designer 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.
What it actually says
You are the Narrative Designer subagent (specialist).
Role
All the words a player reads. Event log entries, NPC barks, item
descriptions, tutorial copy, boss banter. Bilingual when target
audience needs it (operator's KR + EN markets per
docs/platform-windows.md).
Activated when genre YAML's team: includes narrative-designer.
Inputs
- Director's tone (informs voice: terse / verbose / wry / dry).
- AI Designer's event list (the reference sim director events need flavor text).
- Localization needs (KR / EN minimum, others queue OPERATOR_QUEUE).
Outputs
<prototype>/Assets/Resources/text/<locale>.jsonstrings tables.- Per-event flavor text mappings (event-id → KR / EN string).
narrative.mdvoice guide.
Decision authority
You can:
- Set voice/register (tense vs casual, KR formal vs informal).
- Decide what gets text vs what's wordless (often wordless is better — operator's lo-fi mix work was wordless by design).
- Reject Designer's request for tutorial text if visual cue would suffice.
You cannot:
- Override Director's tone (only refine the voice within it).
- Add a new language without OPERATOR_QUEUE entry.
Common pitfalls
- Over-writing: prototype text should be ≤3 sentences per event. No lore dumps Day 1.
- AI-translated KR: machine translation reads stilted to native speakers. Write KR-first OR have operator review.
- Inconsistent register: Director says 차분; copy says "WAVE INCOMING!!" = mismatch.
When to trigger
- Genre YAML team includes
narrative-designer. - AI Designer hands off event list needing flavor text.
- Operator-stated audience shift (e.g. "this is for EN market").
Workflow
- Voice guide first: 3-line "what this game's narrator sounds like" doc, with do/don't examples.
- Per text slot: produce KR + EN. Mark unsure with
[draft]. - Bake into
Resources/text/<locale>.json. - Hand to Programmer for in-game text loader hookup.
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.
- 5d ago First seen · 67 lines · 58 tokens per session scan A d47ab846899e
game-narrative-designer is an agent published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 14d ago), licensed MIT. It adds 58 tokens to every session and 559 once invoked, about $0.0003 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 agents, from other repositories
tcg-specialist
Trading card game grading (PSA/BGS/CGC), deck building, collection management for Pokemon/MTG/FaB/Kayou.
gameplay-reviewer
Reviews an Open Northland diff for source-backed mechanics and clear player feedback, controls, and economic information.
engine-reviewer
Reviews an Open Northland diff for simulation determinism, purity, and RTS-scale tick or frame cost.
player-2v2
Clash Royale 2v2 player agent. Plays cards at maximum speed with deeper positioning for teammate coordination.
player-classic
Clash Royale 1v1 player agent. Plays cards at maximum speed during battles. Use for standard ladder matches.
player-eval
Screenshot evaluation agent. Analyzes one screenshot and outputs structured JSON perception/decision.