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/audit-card-parsing/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/audit-card-parsing)<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.
<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>- 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 | $0.00049 | $0.03441 |
| Opus 5 | $0.00024 | $0.01721 |
| Sonnet 5 | $0.00010 | $0.00688 |
| Haiku 4.5 | $0.00005 | $0.00344 |
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.
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--aftervalue 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
Unimplementedeffects in the entire ability tree (including sub_ability, else_ability, mode_abilities) - Zero
Unknowntrigger modes - Zero
Unknownkeywords - At least one parsed item (abilities + triggers + static_abilities + replacements > 0)
- Oracle text longer than 20 characters (skip vanilla creatures)
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.
- 9d ago First seen · 243 lines · 49 tokens per session scan A 55940907bd69
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.
Other skills, from other repositories
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.
verify
Build/launch/drive recipe for verifying apps/docs changes at runtime (demos, docs pages, llms.txt).
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.