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 skills/melons/melons-agents/pawnsimnpx skills add MelonS/MelonS-Agents --skill pawnsimgit 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/skills/melons/melons-agents/pawnsim)<a href="https://agentmods.dev/skills/melons/melons-agents/pawnsim"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/pawnsim.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 | $0.00033 | $0.00857 |
| Opus 5 | $0.00016 | $0.00428 |
| Sonnet 5 | $0.00007 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
pawnsim 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 4d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pawnsim
Unity mini colony-sim-style colony sim vertical slice, built in 7 days
using game-dev-agent for asset generation,
code scaffolding, balance tuning, and in-game AI Director.
Reference game
콜로니 심 장르. We're building a vertical slice — NOT a clone, NOT competing. Demonstration only.
Scope (locked at start of Day 1)
| Included | Excluded |
|---|---|
| 2-3 pawns | 10+ pawns |
| 3 needs (food, sleep, mood) | 8+ needs |
| 2 resources (wood, food) | full economy + production chains |
| 3-4 actions (chop, eat, sleep, wander) | building, crafting, research |
| 50×50 tilemap | open world / multiple biomes |
| AI Director — 3-5 event types | seasons, weather sim, raids |
| Utility AI (highest-need priority) | mood / relationship simulation |
| Basic save/load (JSON) | autosave / multi-slot / cloud |
| Top-down 2D | 3D / isometric |
End-of-day deliverable schedule
| Day | What .exe shows when launched |
|---|---|
| 1 | Title → Start → empty tilemap + 1 idle pawn, clickable |
| 2 | Pawn moves on right-click, needs UI panel ticking down |
| 3 | Trees on map, pawn can chop wood, wood counter rises |
| 4 | 3 pawns, autonomous needs satisfaction (utility AI) |
| 5 | AI Director generates random events (LLM-driven text) |
| 6 | Save/load works, BGM + SFX added |
| 7 | Polish + demo video + portfolio README |
Each day = builds/day-X-2026-MM-DD.exe snapshot saved.
Directory layout
games/pawnsim/
├── SKILL.md (this file)
├── unity-project/ # Unity 2022.3.32f1 project root
│ ├── Assets/
│ │ ├── Scripts/ # C# (generated by code_assist module)
│ │ ├── Sprites/ # 2D art (generated by asset_gen module)
│ │ ├── Audio/ # BGM + SFX (generated by audio_gen module)
│ │ ├── Configs/ # ScriptableObject balance data
│ │ └── Scenes/
│ ├── Packages/
│ └── ProjectSettings/
├── builds/ # End-of-day .exe snapshots (gitignored)
│ ├── day-1-2026-05-26.exe
│ └── ...
└── docs/
├── DESIGN.md # Scope + system list
├── AGENT_LOG.md # What the agent did each day
└── DEMO.md # Demo video script + portfolio narrative
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- docs/art-style-guide-v3.md 8.9 KB
- docs/art-tone-decisions-2026-07-25.md 14 KB
- docs/art-value-hierarchy-2026-07-29.md 14 KB
- docs/artv2-style-spec.md 6.0 KB
- docs/asset-pack-candidates-2026-07-25.md 12 KB
- docs/audit-genre-fidelity-2026-05-29.md 16 KB
- docs/AUTONOMOUS_SESSION_SUMMARY.md 35 KB
- docs/autonomous-decisions.md 12 KB
- docs/balance-parity-2026-07-25.md 31 KB
- docs/check-round-1.md 4.7 KB
- docs/check-round-2.md 3.3 KB
- docs/check-round-3.md 4.6 KB
- docs/check-round-4.md 8.6 KB
- docs/check-round-5.md 4.2 KB
- docs/check-round-6.md 3.0 KB
- docs/check-round-7.md 3.1 KB
- docs/check-round-8.md 5.0 KB
- docs/cleanup-after-submission.md 3.5 KB
- docs/colony-loop-2026-07-30.md 29 KB
- docs/demo-interview-2026-07-27.md 7.6 KB
- docs/design-immersion-2026-06-11.md 4.2 KB
- docs/design-improvement-backlog.md 27 KB
- docs/design-qa.md 4.2 KB
- docs/design-social-2026-07-24.md 5.1 KB
- docs/external-research-openmmo-2026-08-12.md 8.0 KB
- docs/figures/01-morning.png 1292 KB
- docs/figures/02-midday.png 1378 KB
- docs/figures/03-work-priority.png 847 KB
- docs/figures/04-night.png 996 KB
- docs/figures/05-shadow-times.png 1005 KB
- docs/first-cycle-backlog-2026-06-12.md 28 KB
- docs/first-cycle-walkthrough-2026-06-13.md 2.3 KB
- docs/fun-rubric.md 8.7 KB
- docs/gameloop-backlog-2026-06-11.md 11 KB
- docs/gameplay-audit-2026-07-24.md 16 KB
- docs/GDD.md 12 KB
- docs/genre-comparison-v2.md 15 KB
- docs/genre-comparison.md 27 KB
- docs/genre-gap-backlog-2026-06-12.md 12 KB
- docs/goal.md 4.3 KB
- docs/grader-soak-r2-2026-06-12.md 3.2 KB
- docs/grader-soak-r3-2026-06-12.md 2.1 KB
- docs/grader-soak-r4-2026-06-12.md 2.8 KB
- docs/grader-soak-r5-2026-06-12.md 2.1 KB
- docs/grader-soak-r7-2026-06-13.md 1.9 KB
- docs/grader-soak-r8-2026-06-13.md 2.2 KB
- docs/grader-soak-r9-2026-06-13.md 4.8 KB
- docs/hackathon-bar-analysis-2026-07-24.md 16 KB
- docs/HISTORY_SNS.md 1.4 KB
- docs/HISTORY.md 7.6 KB
- docs/human-play-gap-2026-06-12.md 6.5 KB
- docs/incident-2026-07-26-ts-guid-clobber.md 3.8 KB
- docs/known-limitations.md 3.1 KB
- docs/legibility-and-progression-2026-07-31.md 29 KB
- docs/live-verification-2026-07-29.md 11 KB
- docs/lookfeel-research-2026-07-24.md 25 KB
- docs/lookfeel-round-2026-07-24.md 7.9 KB
- docs/MILESTONES.md 15 KB
- docs/mood-deficit-analysis-2026-06-14.md 3.2 KB
- docs/nan2026-positioning-2026-07-29.md 12 KB
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.
- 4d ago First seen · 91 lines · 33 tokens per session scan A f091b1537a0b
pawnsim is a skill published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 12d ago), licensed MIT. It adds 33 tokens to every session and 857 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
ui_ux_mastery
UI/UX design governance — design systems, accessibility audits, performance budgets, agentic UX patterns.
ui-ux-and-feedback
Use when designing, auditing, or generating a HUD, menu system, or feedback vocabulary for any genre — information hierarchy, diegetic vs. non-diegetic classification, cognitive load budgeting, feedback channel design, menu flow, input modality, and accessibility. Also use to diagnose a UI that is cluttered, that…
unity-editor-tool-developer
Skill "unity-editor-tool-developer" from TravisLeeeeee/awesome-openclaw-personas, covering 🎯 your core mission, 📋 your technical deliverables, custom editorwindow — asset auditor, 1. tool specification and 2. prototype first.
game-asset-generation-cellcog
Game development assets and prototypes with character consistency across all assets.
build-awwwards-quality-sites
Art-direct and implement distinctive, motion-rich marketing, editorial, portfolio, and landing websites with original reference-inspired imagery, standout heroes, GSAP choreography, one smooth-scroll engine, optional Three.js shaders, honest icon and logo sourcing, photo avatars, accessibility, and performance…
viewport
Control the Unreal Editor level viewport — camera type/position, view mode, FOV, exposure, layout, and rendering settings (ViewportService). Use when the user asks to move the editor camera, change the view mode (Lit/Unlit/Wireframe), set FOV/exposure, switch viewport layout, or frame the level for a screenshot.