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 agentmods add skills/xdg/xdg-claude/code-structurenpx skills add xdg/xdg-claude --skill code-structuregit clone --depth 1 https://github.com/xdg/xdg-claudeWhat 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 | $0.00102 | $0.00619 |
| Opus 5 | $0.00051 | $0.00309 |
| Sonnet 5 | $0.00020 | $0.00124 |
| Haiku 4.5 | $0.00010 | $0.00062 |
Grade A, and why
code-structure 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 3d 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.
What it actually says
code-structure
When the question is "list the X in Y", do not Read the whole file. Get an outline first; Read selectively after.
Trigger discrimination
- "list / show / all the methods/classes/exports in ..." -- outline (this skill)
- "where is X defined" / "find calls to X" -- search (rg or ast-grep)
- "how does X work" / "what does X do" -- Read
Tiered approach
-
ast-grep outline-- the default. One interface across languages, no build or import step, and every text view carries line numbers so you can Read just the range you need afterward. Pass-lto be safe (required for stdin; inferred from extension for paths).- File outline:
ast-grep outline -l go file.go(digest: signatures + member names) - Cheapest survey:
ast-grep outline -l go file.go --view names - Drill one symbol's members:
ast-grep outline -l go file.go --match Visitor --view expanded - Directory's exported surface:
ast-grep outline -l go ./pkg - Filter by kind:
--type struct,function; by name:--match REGEX; public members only:--pub-members - Dependency check:
ast-grep outline -l go file.go --items imports - Machine-readable:
--json=compact(alsopretty,stream)
- File outline:
-
Compiler/parser-aware tool when you need true export semantics or docstrings, which outline does not carry:
- Go:
go doc -all ./path/to/pkg - Python:
python -m pydoc some.module.path(requires the module to be importable -- deps installed, onPYTHONPATH) - TS/JS third-party:
cat node_modules/<pkg>/dist/index.d.ts-- the declaration file is a pre-made API outline - Java:
javap -p <Class>(requires compiled.classfiles)
- Go:
-
ctags fallback -- for languages outline's bundled rules don't cover; canonical for C/C++:
ctags -f - file | grep -v '^!' | cut -f1,4 # symbol + kind
Use the outline to decide what to Read, then Read just that section.
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.
- 3d ago First seen · 39 lines · 102 tokens per session scan A 1d5e36ad71ec
code-structure is a skill published in the GitHub repository xdg/xdg-claude (20 stars, last pushed 13d ago), licensed Apache-2.0. It adds 102 tokens to every session and 619 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…