gql-query-writer

gql-query-writer is a skill for Claude Code from leonaero/leon_software_marketplace. It costs 44 tokens per session (3,577 once invoked), scanned A, original, Apache-2.0.

A helper for writing GraphQL queries, which are structured requests for data from an API, against Leon Software’s live API schema.

In plain words
What is it for?
Use it to help external integrators create and check queries for the Leon GraphQL API. It can also identify when a requested API element does not exist.
Why use it?
It helps prevent invalid queries caused by guessing field names, arguments, types, or other schema details.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the leon-api-tools plugin — 3 skills shipped together

Good fit Use it to help external integrators create and check queries for the Leon GraphQL API. It can also identify when a requested API element does not exist.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leonaero/leon_software_marketplace/gql-query-writer
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 leonaero/leon_software_marketplace --skill gql-query-writer
Clone the repo
git clone --depth 1 https://github.com/leonaero/leon_software_marketplace

Made for: Claude Code.

Or install leon-api-tools, the plugin that ships this one along with the rest of its 3 skills.

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 gql-query-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/leonaero/leon_software_marketplace/gql-query-writer/github.svg)](https://agentmods.dev/skills/leonaero/leon_software_marketplace/gql-query-writer)
Your own site
<a href="https://agentmods.dev/skills/leonaero/leon_software_marketplace/gql-query-writer"><img src="https://agentmods.dev/badge/skills/leonaero/leon_software_marketplace/gql-query-writer/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 gql-query-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/leonaero/leon_software_marketplace/gql-query-writer"><img src="https://agentmods.dev/badge/skills/leonaero/leon_software_marketplace/gql-query-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,577 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00044 $0.03577
Opus 5.5 $0.00018 $0.01431
Sonnet 5.5 $0.00009 $0.00715
Haiku 4.5 $0.00004 $0.00358

Measured 2mo ago against content hash f7d80158b6bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gql-query-writer scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_query.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Run this Bash command exactly once** at the start. Do NOT use WebFetch or curl — the schema endpoint is HTTP-only and WebFetch breaks it.
leon-api-tools/skills/gql-query-writer/SKILL.md · 427 lines

How it starts

The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: GraphQL Query Writer — Leon API

You are a GraphQL expert helping the Leon Software Support team assist external integrators in writing correct queries against the Leon GraphQL API.

Integrator's request: $ARGUMENTS


CRITICAL RULE — NO HALLUCINATIONS

⚠️ You MUST NEVER invent, guess, or assume the existence of any type, field, argument, query, mutation, or enum value.

Every single element you use in a query — root query/mutation name, type name, field name, argument name, argument type, enum value — MUST be verified against the live schema fetched in Step 1.

If a field or type does not exist in the schema, you MUST say so explicitly instead of inventing an alternative.

This is non-negotiable. A wrong query sent to a client is worse than no query at all.


STEP 1 — Fetch the live schema (run ONCE, reuse for all steps)

Run this Bash command exactly once at the start. Do NOT use WebFetch or curl — the schema endpoint is HTTP-only and WebFetch breaks it.

Path note: The skill base directory is provided at the top of this prompt (Base directory for this skill: ...). Use it to build the full path to scripts/validate_query.py.

python {SKILL_BASE_DIR}/scripts/validate_query.py --dump-schema --refresh 2>/dev/null

This command:

  • Auto-installs required packages silently (no user prompts)
  • Downloads the schema from S3 and caches it locally in .schema_cache.json
  • Prints a complete structured schema summary to stdout
  • Status messages go to stderr (2>/dev/null suppresses them)

⚠️ Run this command ONLY ONCE per conversation. Store the entire output in memory and use it for Steps 2–7. Do NOT re-run --dump-schema to look something up — search your already-captured output instead.

The output contains:

  • === ROOT QUERIES === — all available queries with arguments and return types
  • === ROOT MUTATIONS === — all available mutations
  • === TYPES === — all types with their fields, argument signatures, and deprecation warnings (⚠️ DEPRECATED)

Read the full file on GitHub · 427 lines

Files

What ships with it

3 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.

  1. 2mo ago First seen · 427 lines · 44 tokens per session scan A f7d80158b6bd

Subscribe to this mod's changes

gql-query-writer is a skill published in the GitHub repository leonaero/leon_software_marketplace (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 3,577 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

gql-query-writer compared with skills from other repositories

gql-query-writer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gql-query-writerleonaero/leon_software_marketplaceSkill24mo agoApache-2.0A44Claude Code
mem0-oss-to-platformmem0ai/mem0Skill69ktodayApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2ktodayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2ktodayMITA46Claude Code
api-designericrisco/rsc-harnessSkill5032d agoMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill252yesterdayMITA106Claude Code
telnyx-messaging-hosted-curlteam-telnyx/aiSkill224todayMITA45Claude Code