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 xmake-io/xmake-skills --skill xmake-introspectiongit clone --depth 1 https://github.com/xmake-io/xmake-skillsWrote 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/xmake-io/xmake-skills/xmake-introspection)<a href="https://agentmods.dev/skills/xmake-io/xmake-skills/xmake-introspection"><img src="https://agentmods.dev/badge/skills/xmake-io/xmake-skills/xmake-introspection/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/xmake-io/xmake-skills/xmake-introspection"><img src="https://agentmods.dev/badge/skills/xmake-io/xmake-skills/xmake-introspection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.01093 |
| Opus 5 | $0.00041 | $0.00547 |
| Sonnet 5 | $0.00016 | $0.00219 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
xmake-introspection 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 11d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Introspection
xmake.lua is a script, not a manifest: values can come from options, packages, rules,
on_config hooks and the toolchain. Reading the file tells you what the author wrote,
not what the build resolves to. Ask xmake instead.
Show project information
xmake show # project name, version, toolchains, targets ...
xmake show -t hello # everything resolved for one target
xmake show -l targets # list target names
xmake show -l toolchains # what toolchains this xmake knows
xmake show -l rules # builtin + project rules
xmake show -l policies # policy names and their defaults
xmake show -l packages # required packages of this project
xmake show -l envs # the environment variables xmake reads
Machine-readable output
Any show output can be emitted as JSON, which is what you want when a script or an agent
consumes it:
xmake show --format=json # whole project as json
xmake show -t hello --format=json # one target as json
xmake show -l targets --format=json
xmake show --format=json --pretty # indented, easier to read in a terminal
::: tip
--json still works but is deprecated, use --format=json.
:::
Query one field without a json parser:
xmake show -t hello --format=json | grep -o '"sourcefiles":[^]]*]'
Dependency graphs
The target dependency graph, as text, JSON, or graphviz DOT:
xmake show --info=depgraph # human readable tree
xmake show --info=depgraph --target=app # only the subtree of one target
xmake show --info=depgraph --format=json # for tooling
xmake show --info=depgraph --format=dot # graphviz
xmake show --info=depgraph --format=dot | dot -Tsvg -o deps.svg
The package dependency graph comes from xrepo:
xrepo info --depgraph zlib
Ask Lua directly
Anything the show plugin does not print is still reachable from a script, and this is the most precise way to answer "what does the build actually see":
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.
- 11d ago First seen · 115 lines · 81 tokens per session scan A 40be22391689
xmake-introspection is a skill published in the GitHub repository xmake-io/xmake-skills (24 stars, last pushed 19d ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,093 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.