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/validate-cr-annotations/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/validate-cr-annotations)<a href="https://agentmods.dev/skills/phase-rs/phase/validate-cr-annotations"><img src="https://agentmods.dev/badge/skills/phase-rs/phase/validate-cr-annotations/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/validate-cr-annotations"><img src="https://agentmods.dev/badge/skills/phase-rs/phase/validate-cr-annotations.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 | $0.00068 | $0.01803 |
| Opus 5.5 | $0.00027 | $0.00721 |
| Sonnet 5.5 | $0.00014 | $0.00361 |
| Haiku 4.5 | $0.00007 | $0.00180 |
Grade A, and why
validate-cr-annotations 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CR Annotation Validation
This skill enforces the mandatory verification protocol for MTG Comprehensive Rules annotations. Every CR number is verified by grep before it is written. No exceptions.
Verification Protocol
For every CR number you are about to write, run this BEFORE writing:
grep -n "^NNN.X" docs/MagicCompRules.txt
Where NNN.X is the rule number (e.g., 702.33d, 613.1f, 120.2a).
- If the grep returns a matching line → the rule exists. Read the text to confirm it matches your intent.
- If the grep returns nothing → STOP. Do not write the annotation. The rule number is wrong.
Batch verification for multiple annotations
When adding several CR annotations in one change, verify all at once:
for ref in "702.33d" "613.1f" "120.2a"; do
echo "=== CR $ref ==="
grep -n "^${ref}" docs/MagicCompRules.txt | head -2
done
Format Rules
| Format | When to use | Example |
|---|---|---|
| Inline comment | Implementation code | // CR 704.5a: A player with 0 or less life loses the game. |
| Doc comment | Public items (functions, types, variants) | /// CR 704: Checks state-based actions. |
Combined + |
Multiple interacting rules | // CR 702.2c + CR 702.19b: Deathtouch with trample assigns lethal (1) to each blocker. |
Combined / |
Alternative/overlapping rules | // CR 704.3 / CR 800.4: SBAs may have ended the game during phase auto-advance. |
Mandatory rules:
- Prefix is always
CR— neverRule,MTG Rule, or bare numbers - Number format regex:
CR \d{3}(\.\d+[a-z]?)? - Description is mandatory — a bare
CR 704.5awith no explanation is not acceptable - Placement: directly above or inline with the code that implements the rule
Known Hallucination Patterns
These are the error classes found in the full audit of this codebase. Watch for them:
1. Off-by-one section numbers (most common)
The 702.x keyword ability numbers are arbitrary sequential assignments. There is no mnemonic anchor. Common confusions:
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 · 133 lines · 68 tokens per session scan A ba61ecc6bdbe
validate-cr-annotations is a skill published in the GitHub repository phase-rs/phase (312 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 1,803 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
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…