Instructions for hxq, a command-line tool that understands the structure of Haxe source code.

It helps query Haxe files and directories, inspect code, and perform supported code changes with the correct command and paths.

It helps navigate and change Haxe files using their code structure instead of only searching text.

hxq — Skill for Claude Code by AxGord

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add AxGord/claude-workflow --skill hxq

Clone the repo

git clone --depth 1 https://github.com/AxGord/claude-workflow

Made for: Claude Code.

Or install workflow, the plugin that ships this one along with the rest of its 28 skills, 2 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/axgord/claude-workflow/hxq/github.svg)](https://agentmods.dev/skills/axgord/claude-workflow/hxq)

Your own site

<a href="https://agentmods.dev/skills/axgord/claude-workflow/hxq"><img src="https://agentmods.dev/badge/skills/axgord/claude-workflow/hxq/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/axgord/claude-workflow/hxq"><img src="https://agentmods.dev/badge/skills/axgord/claude-workflow/hxq.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,217 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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.08217
Opus 5	$0.00008	$0.04109
Sonnet 5	$0.00003	$0.01643
Haiku 4.5	$0.00002	$0.00822

Measured 9d ago against content hash e7fcbec40272, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hxq 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.

templates/skills/hxq/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hxq — structural Haxe query CLI

hxq <subcommand> [opts] <file-or-dir-or-glob>... parses .hx files with anyparse's own parser. Invoke as bare hxq (on PATH) — never ./bin/hxq. Auto-adds --lang haxe.

ONE command for EVERYTHING — hxq. hxq runs BOTH the read/query subcommands AND the write/mutation ops below (it forwards every subcommand to the engine). apq is a documentation label, NOT an installed command — wherever this skill writes apq <op>, RUN it as hxq <op>. Never node bin/apq.js (bypasses the shim and needs cwd=project). Never cd — hxq is on PATH and cwd-independent; pass project-relative paths (default cwd = project root) or absolute paths, and use hxq probe '<code>' for throwaway snippets instead of /tmp scratch files. (USER decision; root cause = the apq/hxq dual-naming where only hxq is installed.)

Path arguments: prefer relative. hxq respects CWD; relative paths give shorter hit lines (<file>:line:col) than absolute. Use absolute only for files outside the current project.

Works on ANY .hx, including EXTERNAL forks / other repos. hxq parses by the anyparse grammar regardless of which project a file lives in — refs/uses/ast/search/source all work cross-project (e.g. querying a haxe-formatter fork for ground-truth). Pass the absolute path. Do NOT grep / node -e readFileSync / git show a fork .hx — that is the recurring crutch reflex. Query it structurally (refs/ast) or read raw lines with hxq source (gate-blessed, below). Most fork files parse; only the few that genuinely skip-parse need hxq source (which reads raw bytes regardless of parse status).

Output: grouped-by-file by default. Walkers print <file>: once then 2-space-indented <line>:<col>: <hit> lines. Pass --flat for legacy <file>:<line>:<col>: <hit> per line (downstream tools).

Build / auto-rebuild

haxe bin/apq-js.hxml builds the JS runner. The hxq shim AUTO-REBUILDS by default when find -newer detects stale .hx under src/; aborts on build failure. Opt-out:

HXQ_AUTO_REBUILD=0 — legacy warn-once-per-mtime mode (cache at $XDG_CACHE_HOME/hxq/warned).
HXQ_QUIET=1 — skip stale check entirely. Takes precedence. ⚠️ NEVER use it for a VERIFICATION probe right after src/ edits — it runs the STALE binary and can "refute" a fix that actually landed (or "confirm" one that didn't). Verification probes need an explicit haxe bin/apq-js.hxml first, or a bare hxq call (auto-rebuild on).

Read the full file on GitHub · 244 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

9d ago First seen · 244 lines · 15 tokens per session scan A e7fcbec40272

Subscribe to this mod's changes

hxq is a skill published in the GitHub repository AxGord/claude-workflow (5 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 8,217 once invoked, about $0.0001 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 2026-08-31.

Languages

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

ast-grep

Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…

JanDeDobbeleer/oh-my-posh · 80 tokens

platform-detection

Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system. Use only for "which test platform/framework?", "VSTest or MTP?", or "what runner does this project use?", including bridge settings, UseVSTest opt-outs, and incompatible or conflicting VSTest/MTP configuration.…

dotnet/skills · 146 tokens

hxq