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 leon-report-buildergit 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/leon-report-builder)<a href="https://agentmods.dev/skills/leonaero/leon_software_marketplace/leon-report-builder"><img src="https://agentmods.dev/badge/skills/leonaero/leon_software_marketplace/leon-report-builder/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/leon-report-builder"><img src="https://agentmods.dev/badge/skills/leonaero/leon_software_marketplace/leon-report-builder.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 | $0.00174 | $0.01975 |
| Opus 5 | $0.00087 | $0.00988 |
| Sonnet 5 | $0.00035 | $0.00395 |
| Haiku 4.5 | $0.00017 | $0.00198 |
Grade A, and why
leon-report-builder 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 12d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Leon Report Builder
Purpose
Report Wizard is organized by "scope" — a data domain, each exposed as a matching pair of tools:
get-report-wizard-<scope>-columns-list (no input, returns the columns available for that
scope) and get-report-wizard-<scope>-report (takes a columnList plus scope-specific filters,
returns the rows). Flight is the only scope available right now. More scopes will be added
over time using the same two-tool pattern — if a request is about a scope that doesn't have
flight-scope tools obviously covering it (e.g. a crew-only or trip-only report), tool_search
for get-report-wizard-<scope> before concluding it isn't supported yet.
This skill describes the general schema for using any Report Wizard scope, not just a fixed
recipe for flight reports — the same workflow applies once new scopes appear. It does not
replace leon-flight-search (which finds/identifies flights) — use this skill specifically when
the goal is a structured, column-based report or export, typically meant to be delivered as a
file.
Core principles
These apply regardless of which scope you're working with:
- Always ask for the desired output format before building anything — HTML, Excel (xlsx), or PDF — if the user hasn't already said. The format determines the downstream tool you hand the data to, so it's worth confirming up front rather than assuming and redoing the work.
- Request the minimum columns that satisfy the request. Don't pull every available column
"just in case" — check the columns-list output, pick only what's needed to answer the request
or populate the report, and add an identifier column (e.g.
unique_idin flight scope) only if you'll need it for a follow-up lookup. - Push filters into the tool call first. Every scope's report tool exposes some filters (for flight scope: aircraft, airports, crew, date range, cancellation). Apply as many of the user's constraints as the tool supports directly as parameters before calling it.
- Only filter in your own code when the tool has no equivalent parameter. If a constraint the user asked for isn't exposed as a filter, fetch the data using whatever filters are available (to keep the result as narrow as possible), then filter the returned rows yourself. Don't skip an available tool-side filter just because you'll also need code-side filtering for something else — combine both rather than doing everything in code.
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.
- 12d ago First seen · 131 lines · 174 tokens per session scan A c9d6f3faf1f0
leon-report-builder is a skill published in the GitHub repository leonaero/leon_software_marketplace (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 174 tokens to every session and 1,975 once invoked, about $0.0009 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…