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 wyattowalsh/agents --skill wargamegit clone --depth 1 https://github.com/wyattowalsh/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/wyattowalsh/agents/wargame)<a href="https://agentmods.dev/skills/wyattowalsh/agents/wargame"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/wargame/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/wyattowalsh/agents/wargame"><img src="https://agentmods.dev/badge/skills/wyattowalsh/agents/wargame.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 108 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 9 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.07172 |
| Opus 5.5 | $0.00015 | $0.02869 |
| Sonnet 5.5 | $0.00008 | $0.01434 |
| Haiku 4.5 | $0.00004 | $0.00717 |
Grade A, and why
wargame 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 1mo 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 — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wargame
Domain-agnostic strategic decision analysis. Every output labeled exploratory.
Canonical Vocabulary
Use these terms exactly throughout all modes:
| Term | Definition |
|---|---|
| scenario | The situation under analysis — includes trigger event, stakeholders, constraints, and decision space |
| actor | An entity in the wargame with goals, resources, and constraints; may be user-controlled or AI-controlled |
| turn | One cycle of the interactive wargame loop: situation brief, decision, adjudication, consequences |
| adjudication | The process of resolving a turn's decisions into outcomes using probability and game state |
| monte carlo | Randomized exploration of N outcome variations from a single decision point (N <= 25) |
| inject | A pre-seeded unexpected event deployed mid-game to force trade-offs between competing objectives |
| tier | Complexity classification: Clear (0-3), Complicated (4-6), Complex (7-10), Chaotic (9-10) |
| AAR | After Action Review — mandatory end-of-game analysis extracting biases, insights, and transferable principles |
| journal | The saved markdown record of an analysis or wargame session, stored in `~/.{gemini |
| action bridge | Three-level commitment framework: Probe (low-cost test), Position (reversible move), Commit (irreversible) |
| criteria | User-ranked decision dimensions (e.g., Speed, Cost, Risk) that weight option evaluation |
| bias sweep | Systematic check for human and LLM biases per references/cognitive-biases.md protocol |
| rewind | Load a previous turn's state snapshot and fork the journal to explore an alternate path |
| difficulty | Adjudication harshness: optimistic, realistic, adversarial, worst-case |
Dispatch
| $ARGUMENTS | Action |
|---|---|
| Scenario text (specific) | → Classification → Criteria → Analysis |
| Vague/general input | → Research → Interview → Confirmation → Classification |
| `resume [# | keyword]` |
list [filter] |
Show journal metadata table (optional filter: active, domain, tier) |
archive |
Archive journals older than 90 days (when count > 20) |
delete N |
Delete journal N with confirmation |
meta |
Cross-journal decision fitness analysis |
compare [j1] [j2] |
Side-by-side comparison of two journal runs |
summary [N] |
Condensed summary of completed journal N (10-20 lines) |
tutorial |
Run guided 2-turn pedagogical scenario |
facilitated |
Start facilitated multiplayer mode (LLM as game master only) |
| Empty | Show scenario gallery + "guide me" |
What ships with it
21 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.
- evals/complexity-classification.json 1.0 KB
- evals/evals.json 2.2 KB
- evals/scenario-setup.json 1.2 KB
- references/cognitive-biases.md 5.6 KB
- references/dashboard-schema.md 3.9 KB
- references/frameworks-procedures.md 8.7 KB
- references/frameworks.md 4.8 KB
- references/output-formats-commands.md 12 KB
- references/output-formats-core.md 22 KB
- references/session-commands.md 10 KB
- references/visualizations.md 6.9 KB
- references/wargame-engine.md 27 KB
- scripts/asset_toolkit/__init__.py 303 B runs code
- scripts/asset_toolkit/_shared.py 5.6 KB runs code
- scripts/asset_toolkit/common.py 3.0 KB runs code
- scripts/asset_toolkit/package.py 43 KB runs code
- scripts/asset_toolkit/validate_evals.py 11 KB runs code
- scripts/asset_toolkit/validate_hooks.py 13 KB runs code
- scripts/asset_toolkit/validate_skill.py 3.6 KB runs code
- scripts/check.py 2.2 KB runs code
- templates/dashboard.html 44 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.
- 1mo ago First seen · 510 lines · 38 tokens per session scan A cbf1f3bca263
wargame is a skill published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 7,172 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…