latexml-oxide: Skill for Claude Code

.claude/skills/perf-check/SKILL.md

perf-check is a skill for Claude Code from dginev/latexml-oxide. It costs 85 tokens per session (1,323 once invoked), scanned A, original, CC0-1.0.

A guide for measuring how quickly latexml-oxide converts LaTeX documents and for choosing among its Rust build profiles. LaTeX is a document-formatting system, and latexml-oxide converts its documents into other formats.

In plain words
What is it for?
Use it when benchmarking conversions, comparing latexml-oxide with Perl, selecting a build profile, or investigating slow or memory-heavy conversions.
Why use it?
It prevents misleading benchmark comparisons, such as measuring a debug build when a release build is needed. It also records optimization questions that have already been tested so they do not have to be investigated again.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is dginev/latexml-oxide's own configuration. It tells Claude Code how to work on latexml-oxide 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 latexml-oxide configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dginev/latexml-oxide. 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/dginev/latexml-oxide/main/.claude/skills/perf-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dginev/latexml-oxide

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 perf-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/dginev/latexml-oxide/perf-check.svg)](https://agentmods.dev/skills/dginev/latexml-oxide/perf-check)
Your own site
<a href="https://agentmods.dev/skills/dginev/latexml-oxide/perf-check"><img src="https://agentmods.dev/badge/skills/dginev/latexml-oxide/perf-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,323 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.
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 $0.00085 $0.01323
Opus 5 $0.00043 $0.00661
Sonnet 5 $0.00017 $0.00265
Haiku 4.5 $0.00009 $0.00132

Measured 7d ago against content hash 072c91c6087d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

perf-check 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 7d 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/perf-check/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build profiles — use the right one (Cargo.toml)

Profile Command Use
test (default) cargo build / cargo test / cargo run All day-to-day dev + triage. Full debug info, debug-assertions, overflow-checks, fast incremental. Best diagnosability.
ci cargo test --profile ci GitHub runner only (16 GB, fast compile). NOT what local dev should mimic.
release cargo build --release Sandbox sweeps + Perl-parity measurement. Strong-optimized, thin-LTO.
maxperf cargo build --profile maxperf Distribution artifact. Fat-LTO, CGU=1, panic=abort. Slowest build; smallest+fastest binary.

Distribution recipe (what tools/make_release.sh uses): cargo build --no-default-features --features runtime-bindings --profile maxperf --bin latexml_oxide.

Settled questions — DO NOT re-open (measured, closed, tooling deleted)

  • PGO / target-cpu (x86-64-v3, native): NO measurable gain. Rigorous measurement (2026-06-21, disjoint train/measure split, best-of-3 interleaved): total speedup 0.999×, identical medians. maxperf is already at the compiler ceiling (fat-LTO + CGU=1 captures what PGO would unlock on thin-LTO), and the hot path (branchy catcode/macro dispatch) is neither SIMD-amenable nor statically branch-skewed. Ship the portable x86-64 baseline. Do not re-attempt without a major engine-architecture change. (pgo-isa-no-gain-2026-06-21 memory; docs/performance/PERFORMANCE.md.)
  • Startup floor (~161 ms): the ~50 ms dump-parse lever was declined. Decomposed: proc init ~6 ms, bootstrap ~9 ms, latex dump load ~85 ms (60% text-parse), _constructs+digest+build+serialize ~80 ms. The clean lever (binary dump format / parallel-parse) is ~50 ms ≈ 10% of the 507 ms median — declined as too small to justify the dump-pipeline parity re-validation risk. Compiling dumps to Rust code (vs gzip-blob embed) cost +10 min compile for zero win, abandoned. Do not optimize the dump load. (docs/archive/STARTUP_COST_ANALYSIS_2026-06-21.md.)

Read the full file on GitHub · 80 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. 7d ago First seen · 80 lines · 85 tokens per session scan A 072c91c6087d

Subscribe to this mod's changes

perf-check is a skill published in the GitHub repository dginev/latexml-oxide (11 stars, last pushed yesterday), licensed CC0-1.0. It adds 85 tokens to every session and 1,323 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

inclusio-publisher

Drive the inclusio publishing engine via MCP — render, audit, and report on PDF/UA-2 tagged documents.

sebastienrousseau/inclusio · 30 tokens

Paper Writing Skills Index

Routing and workflow skill family for paper-writing tasks. Covers manuscript drafting, journal and conference papers, grant proposals, lab reports, group-meeting reports, talks, workshop notes, reviewer rebuttals, academic HTML/PDF/LaTeX output with editable-block contracts, citation grounding, evidence checking, and…

aristoteleo/PantheonOS · 76 tokens

test-iterate-loop

Autonomously diagnose a codebase, apply minimal fixes, and rerun tests until they pass or a real blocker is reached. Use when the user explicitly requests an iterative fix-until-green loop across Python, R, Julia, or HPC workflows.

flonat/flonat-research · 55 tokens

postmortem

Deliver a structured post-mortem after incidents, mistakes, or stuck sessions. Use when the user requests a structured post-mortem after incidents, mistakes, or stuck sessions.

flonat/flonat-research · 40 tokens

code-archaeology

Recover the structure, intent, and lineage of old code, data, or analysis files. Use when inherited or dormant research code must be understood before it is changed. Not for a quality review of already-understood code.

flonat/flonat-research · 50 tokens

check-pipeline

Check that a code and its Pipeline/ .md are still compatible — that every symbol, cell number, data file, and data-flow claim in the pipeline doc still matches the current code (drift detection). Use after editing a documented notebook/engine/script, before trusting a pipeline doc, or on request ("does the pipeline…

Mexregkan/claude-for-researchers · 106 tokens