phase: Skill for Claude Code

.claude/skills/audit-card-parsing/SKILL.md

audit-card-parsing is a skill for Claude Code from phase-rs/phase. It costs 49 tokens per session (3,441 once invoked), scanned A, original, Apache-2.0.

A review process for card data that compares the parsed structure of each card with its original Oracle rules text. Oracle text is the official rules wording used for a card.

In plain words
What is it for?
Use it to audit supported cards, continue an earlier audit, split the work into batches, and track open or fixed parsing problems.
Why use it?
It finds cards that appear supported but were parsed incorrectly, such as cards with missing abilities, wrong effects, targets, amounts, or conditions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is phase-rs/phase's own configuration. It tells Claude Code how to work on phase itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything phase configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/phase-rs/phase/main/.claude/skills/audit-card-parsing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/phase-rs/phase

Made for: Claude Code.

Wrote 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.

agentmods badge for audit-card-parsing

README.md
[![agentmods](https://agentmods.dev/badge/skills/phase-rs/phase/audit-card-parsing/github.svg)](https://agentmods.dev/skills/phase-rs/phase/audit-card-parsing)
Your own site
<a href="https://agentmods.dev/skills/phase-rs/phase/audit-card-parsing"><img src="https://agentmods.dev/badge/skills/phase-rs/phase/audit-card-parsing/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.

agentmods 80×15 button for audit-card-parsing

Your own site · 80×15
<a href="https://agentmods.dev/skills/phase-rs/phase/audit-card-parsing"><img src="https://agentmods.dev/badge/skills/phase-rs/phase/audit-card-parsing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.03441
Opus 5 $0.00024 $0.01721
Sonnet 5 $0.00010 $0.00688
Haiku 4.5 $0.00005 $0.00344

Measured 9d ago against content hash 55940907bd69, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

audit-card-parsing 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 9d 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.

.claude/skills/audit-card-parsing/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Card Parsing Accuracy

Semantically compare the parsed JSON ability structures in client/public/card-data.json against the raw Oracle text for each card. Find cards that the coverage system considers "supported" (no Unimplemented effects, no Unknown triggers/keywords) but whose parsed structures are semantically incorrect — wrong effect type, wrong target, wrong amount, missing abilities, missing conditions, etc.

Subcommands

  • continue — Resume from where the last audit left off. Reads the "Resume Point" section from the report file to get the --after value automatically. Equivalent to /audit-card-parsing --after "<last card>".
  • status — Print a summary of the audit: how many cards audited, how many remaining, number of open vs fixed patterns, and the resume point. Does NOT run any audit — just reads the report file and prints stats.

Parameters

The user may append parameters after invoking this skill:

  • --after "Card Name" — Start processing cards alphabetically after this card name (case-insensitive key). Use this to split work across parallel agents.
  • --limit N — Process N cards per batch (default: 50).
  • --format <format> — Only audit cards legal in this format (e.g., standard, modern, pioneer, commander).
  • --file <path> — Append findings to this report file (default: .planning/parser-audit-report.md).

If no parameters or subcommand given, start from the beginning and process 50 cards.

When continue is used, read the report file's "Resume Point" section to extract the last card key, then proceed as if --after "<that key>" was passed.

Instructions

Step 1 — Extract the batch

Use jq to extract a batch of supported cards from client/public/card-data.json. "Supported" means:

  • Zero Unimplemented effects in the entire ability tree (including sub_ability, else_ability, mode_abilities)
  • Zero Unknown trigger modes
  • Zero Unknown keywords
  • At least one parsed item (abilities + triggers + static_abilities + replacements > 0)
  • Oracle text longer than 20 characters (skip vanilla creatures)

Read the full file on GitHub · 243 lines

Changes

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.

  1. 9d ago First seen · 243 lines · 49 tokens per session scan A 55940907bd69

Subscribe to this mod's changes

audit-card-parsing is a skill published in the GitHub repository phase-rs/phase (269 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 3,441 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 2026-08-30.