Borrowing it
Nothing to install: this file belongs to phase-rs/phase. 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/phase-rs/phase/main/.claude/skills/ai-duel/SKILL.mdgit clone --depth 1 https://github.com/phase-rs/phaseWrote 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/phase-rs/phase/ai-duel)<a href="https://agentmods.dev/skills/phase-rs/phase/ai-duel"><img src="https://agentmods.dev/badge/skills/phase-rs/phase/ai-duel/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/phase-rs/phase/ai-duel"><img src="https://agentmods.dev/badge/skills/phase-rs/phase/ai-duel.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 | $0.00041 | $0.02807 |
| Opus 5.5 | $0.00016 | $0.01123 |
| Sonnet 5.5 | $0.00008 | $0.00561 |
| Haiku 4.5 | $0.00004 | $0.00281 |
Grade A, and why
ai-duel 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Duel Simulation
Run AI-vs-AI game simulations to test decision quality, validate matchups, and catch regressions.
Quick Start
# Default: Red Aggro vs Green Midrange, 5 games, Medium difficulty
rtk cargo run --release --bin ai-duel -- client/public --batch 5
# Single verbose game (see every combat action and spell cast)
rtk cargo run --release --bin ai-duel -- client/public --seed 42 --difficulty VeryHard
# Batch with specific seed for reproducibility
rtk cargo run --release --bin ai-duel -- client/public --batch 20 --seed 1000 --difficulty Medium
# Full registered matchup suite in measurement mode
rtk cargo run --release --bin ai-duel -- client/public --suite --games 10 --seed 42 \
--output target/duel-suite-results.json
# Compare two suite reports with paired-seed sign-test status
rtk cargo run --release --bin ai-duel -- compare crates/phase-ai/baselines/duel-suite.json \
target/duel-suite-results.json
# Commander candidate-seat measurement
rtk cargo run --release --bin ai-duel -- client/public --commander-suite --games 8 --seed 42 \
--difficulty Hard --baseline-difficulty Medium \
--output target/commander-suite-results.json
CLI Options
| Flag | Description | Default |
|---|---|---|
--batch N |
Run N games, print summary only | 1 (verbose) |
--seed S |
RNG seed for reproducibility | time-based |
--difficulty LEVEL |
VeryEasy|Easy|Medium|Hard|VeryHard |
Medium |
--matchup NAME |
Deck matchup preset | red-vs-green |
--list-matchups |
Show available matchups | - |
--verbose |
Print every action (full trace) | off |
--suite |
Run every registered MatchupSpec in measurement mode |
off |
--games N |
Games per matchup/suite cell | 10 for suite, 4 for commander suite |
--output PATH |
JSON report path | target/duel-suite-results.json |
--suite-filter STR |
Run only suite matchups whose id contains STR | all |
--show-attribution |
Capture phase_ai::decision_trace policy attribution |
off |
--commander-suite |
Run 4-player Commander candidate-seat rotations | off |
--baseline-difficulty LEVEL |
Baseline seats for --commander-suite |
Medium |
--feed PATH |
Commander feed under data root | feeds/mtggoldfish-commander.json |
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 · 239 lines · 41 tokens per session scan A 4fb47d2df963
ai-duel is a skill published in the GitHub repository phase-rs/phase (312 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 2,807 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 2026-08-30.
Other skills, from other repositories
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history, or import a local recording. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
graphify-windows
Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md.
lessons
How to propose and query distilled lessons (the experiential memory). Only project-steward persists; every other agent proposes/queries. Use when you discover a durable lesson or need prior experience for the current task.
webgl-standards
DORMANT (ADR-0017, 2026-07-20) - the TERMINAL VELOCITY scroll-film was retired and apps/landing is a static site with no GL surface; this skill is preserved for any future WebGL rebuild (conventions, verified version pins, playhead/scroll-rig/VAT/Gerstner/post-chain patterns, budgets, gate + semantic-layer machinery).…
agent-cli-standards
Agent-facing CLI standards — the argv-sentinel binary mode, the thin-client-over-the-bridge rule, allowlist projections, prompt-fencing third-party text, the stable machine-readable output contract, exit codes, throttling, and destructive-command operability. Load for changes under extensionbridge/agentcli.rs…
webgl-gate-audit
Procedures for auditing apps/landing TERMINAL VELOCITY WebGL phase gates - driving the browser to exact playhead positions across the 9 scenes, screenshot discipline, scrub + VAT determinism (scrub down THEN rewind to the same playhead -> identical frame), FPS sampling at the risk scenes, draw-call + bundle-size…