Borrowing it
Nothing to install: this file belongs to haoyifan/Silicon-Pantheon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/haoyifan/Silicon-Pantheon/master/.claude/skills/scenario-check/SKILL.mdgit clone --depth 1 https://github.com/haoyifan/Silicon-PantheonWrote 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/haoyifan/silicon-pantheon/scenario-check)<a href="https://agentmods.dev/skills/haoyifan/silicon-pantheon/scenario-check"><img src="https://agentmods.dev/badge/skills/haoyifan/silicon-pantheon/scenario-check/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/haoyifan/silicon-pantheon/scenario-check"><img src="https://agentmods.dev/badge/skills/haoyifan/silicon-pantheon/scenario-check.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.02902 |
| Opus 5 | $0.00019 | $0.01451 |
| Sonnet 5 | $0.00008 | $0.00580 |
| Haiku 4.5 | $0.00004 | $0.00290 |
Grade A, and why
scenario-check 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 12d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scenario Validation Skill
You are an experienced game designer and QA engineer reviewing tactical grid combat scenarios for Silicon Pantheon.
Target
- If
$ARGUMENTSis empty or blank: check ALL scenarios ingames/*/config.yaml(skip_test_plugin) - If
$ARGUMENTSis a scenario name (e.g.,03_thermopylae): check only that scenario
Checks to Perform
For each scenario, read the full config.yaml and the locale/zh.yaml (if it exists), then run every check below. Report each issue with severity (CRITICAL / HIGH / MEDIUM / LOW / INFO).
1. Format & Loading (CRITICAL if broken)
- Run
load_scenario(name)via Python to verify the config parses and loads without errors:.venv/bin/python3 -c "from silicon_pantheon.server.engine.scenarios import load_scenario; s = load_scenario('SCENARIO_NAME'); print(f'{s.board.width}x{s.board.height} {len([u for u in s.units.values() if u.owner.value==\"blue\"])}b+{len([u for u in s.units.values() if u.owner.value==\"red\"])}r')" - Every terrain
typeused in board entries must be defined interrain_types move_coston impassable terrain must be99(not1or a string)passable: falsemust accompanymove_cost: 99
2. Unit Placement (CRITICAL if broken)
- No unit placed on an impassable tile (cross-reference positions against
passable: falseterrain) - No unit out of bounds (x must be 0..width-1, y must be 0..height-1)
- No two units on the same tile
- Both teams have at least 3 units
- No unit has ATK 0 or HP 0
3. Glyph & ID Consistency
- No glyph collisions of any kind (HIGH severity). The map renders blue units UPPERCASE, red units lowercase, and terrain glyphs as-is. Three collision types to check:
- Terrain-terrain: No two
terrain_typesmay share the sameglyph— they are visually identical on the map. - Unit-terrain (rendered form): A blue unit's
glyph.upper()must not equal any terrain glyph. A red unit'sglyph.lower()must not equal any terrain glyph. These produce identical characters on the map and the agent cannot distinguish unit from terrain. - Cross-team unit-unit: No blue unit's
glyph.upper()should equal any red unit'sglyph.lower()(i.e., no two units across teams should share the same base letter). While case-distinguishable, this forces the agent to rely on case alone to tell units apart, which wastes reasoning tokens. Fix by changing the conflicting unit glyph to an unused letter. Prefer meaningful mnemonics (first letter of name/role).
- Terrain-terrain: No two
- No
coloris shared between anyunit_classesentry and anyterrain_typesentry (MEDIUM severity when violated) — otherwise a unit parked on a same-color tile becomes visually indistinguishable from the terrain. Units should use team colors (red/bright_red,cyan/bright_cyan,magentafor accents); terrain should use environmental colors (green,blue,yellow,white,bright_black,dim). Fix by changing the terrain color to a nearby unused shade. - Win condition
unit_idvalues must match actual units (format:u_{b|r}_{class}_{N}) reach_tilepositions must be within bounds and NOT on impassable tilesseize_enemy_fortrequires forts to exist- Fort entries should use
ownernotteam
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.
- 12d ago First seen · 141 lines · 38 tokens per session scan A f8ef1c6c253d
scenario-check is a skill published in the GitHub repository haoyifan/Silicon-Pantheon (6 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 2,902 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 2026-08-31.
Other skills, from other repositories
pixel-art
Pixel art w/ era palettes (NES, Game Boy, PICO-8).
minecraft-modpack-server
Host modded Minecraft servers (CurseForge, Modrinth).
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
dashboard-widgets
Author a dashboard widget — a small React component backed by named LangWatchQL queries — from a plain question. Discovers the analytics schema, writes the queries, writes the widget file, saves it, then proves it renders. Use when asked to build, prototype, or iterate on a custom chart widget, or to add a widget…
agent-improve
Turns production evidence into tested improvements for your AI agent. Forms hypotheses from real traces and analytics, explains the reasoning behind each one, then executes with the user: scenario tests that reproduce production failures, prompt and code changes as reviewable PRs, new evaluators and monitors that…