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 magnus919/agent-skills --skill ascii-city-enginegit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/ascii-city-engine)<a href="https://agentmods.dev/skills/magnus919/agent-skills/ascii-city-engine"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/ascii-city-engine/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/magnus919/agent-skills/ascii-city-engine"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/ascii-city-engine.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 | $0.00072 | $0.00914 |
| Opus 5.5 | $0.00029 | $0.00366 |
| Sonnet 5.5 | $0.00014 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00091 |
Grade A, and why
ascii-city-engine 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASCII City Engine
Build a portable city experience in three layers: an engine, a city-provider contract, and a city pack. Keep city-specific facts out of engine code.
Workflow
- Define the pack boundary and local meter-based CRS.
- Acquire elevation, building, and road/path data from public sources.
- Verify downloads, licenses, units, and provenance before conversion.
- Reproject all geometry to local meters and emit the manifest plus world tiles.
- Validate the pack offline:
python3 scripts/validate-city-pack.py path/to/city-pack - Load the pack's first tile in
assets/ascii-city-engine.htmland test movement, grade following, and solid footprints. - Record data limitations and human acceptance evidence.
Required invariants
- Compute
feet_zfrom terrain andeye_zfrom feet plus eye height. - Reject null terrain, over-steep steps, and movement touching a solid footprint.
- Use deterministic building colors and clear missed rays every frame.
- Treat v1 as one ground height per
(x, y)column; reserve, but do not implement, a surface graph. - Keep the engine independent of any city, vendor, agent harness, or private infrastructure.
- Do not commit large or full-resolution source data. Commit only a small redistributable sample; document acquisition for the rest.
Reference routing
- Read references/engine-architecture.md for world math, rendering, collisions, and the scaffold contract.
- Read references/city-provider-contract.md when creating or validating a provider.
- Read references/gis-ingestion.md before downloading or converting GIS sources.
- Read references/raleigh-poc.md for the reproducible Raleigh proof of concept.
- Use templates/city-pack-manifest.schema.json and templates/world.schema.json as authoritative data contracts.
What ships with it
14 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.
- assets/ascii-city-engine.html 16 KB
- assets/deliberately-broken-pack/manifest.json 280 B
- assets/deliberately-broken-pack/README.md 325 B
- assets/raleigh-downtown-sample/manifest.json 1.8 KB
- assets/raleigh-downtown-sample/world/tile-0.json 497 KB
- evals/evals.json 8.1 KB
- README.md 2.0 KB
- references/city-provider-contract.md 3.4 KB
- references/engine-architecture.md 6.3 KB
- references/gis-ingestion.md 5.6 KB
- references/raleigh-poc.md 8.6 KB
- scripts/validate-city-pack.py 15 KB runs code
- templates/city-pack-manifest.schema.json 1.7 KB
- templates/world.schema.json 3.4 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.
- 2mo ago First seen · 64 lines · 72 tokens per session scan A dc1a22de7998
ascii-city-engine is a skill published in the GitHub repository magnus919/agent-skills (154 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 914 once invoked, about $0.0003 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.
Other skills, from other repositories
dream-loop
Build stunning 3D scenes via a concept-art fidelity loop.
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
map
Build and commit a Cortex function knowledge graph — maps structural dependencies and domain intent relationships across all AI functions in the project. Supports --reduce (default on) for transitive reduction of the dependency graph.
cocotrace
Build and query the SHA-256 requirements-to-implementation traceability graph across lifecycle artifacts.
cocowatch
Developer engagement observer — non-blocking, always-on observational layer that tracks Delegation Intensity, Review Depth, and Engagement Zone throughout a session. Summary surfaced at $ship and FULL checkpoints.