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.
npx skills add leonaero/leon_software_marketplace --skill gql-query-writergit clone --depth 1 https://github.com/leonaero/leon_software_marketplaceWrote 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/leonaero/leon_software_marketplace/gql-query-writer)<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.
<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>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 | $0.00044 | $0.03577 |
| Opus 5.5 | $0.00018 | $0.01431 |
| Sonnet 5.5 | $0.00009 | $0.00715 |
| Haiku 4.5 | $0.00004 | $0.00358 |
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.
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. 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 toscripts/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/nullsuppresses 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)
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.
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.
- 2mo ago First seen · 427 lines · 44 tokens per session scan A f7d80158b6bd
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.
gql-query-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gql-query-writerleonaero/leon_software_marketplace | Skill | 2 | 4mo ago | Apache-2.0 | A | 44 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | today | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | today | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | today | MIT | A | 46 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 252 | yesterday | MIT | A | 106 | Claude Code |
| telnyx-messaging-hosted-curlteam-telnyx/ai | Skill | 224 | today | MIT | A | 45 | Claude Code |