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/leifericf/agentic-sdk/check-performancenpx skills add leifericf/agentic-sdk --skill check-performancegit clone --depth 1 https://github.com/leifericf/agentic-sdkWhat 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 | $0.00030 | $0.00923 |
| Opus 5 | $0.00015 | $0.00462 |
| Sonnet 5 | $0.00006 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
check-performance 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 2d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
check-performance
Role: review the shard against the project's performance targets.
Failure model: the code is correct but breaks a real-time or budget commitment, allocates on a hot path, or does work that grows worse than linearly with input the caller controls.
Performance targets are project-specific. Read the design docs and the descriptor for the project's budgets (frame time, callback latency, query cost, scan throughput) before sweeping. What follows is the sweep pattern, not the budget.
Look for
- Allocation on hot paths. A real-time callback (audio, video, input) or a per-frame function that allocates on the steady path: no incidental allocation, no internal collection growth, no formatting inside the loop. A per-keystroke query path must not allocate per call beyond the result vector. Any allocation in these paths is a finding.
- Locks on hot paths. A lock held across an unbounded operation on a real-time or per-frame path. Cross-thread communication on a hot path belongs on a lock-free queue or an atomic, not a mutex.
- Arithmetic that defeats SIMD or the hardware. Inner loops over sampled data written as scalar code when the platform's vector type would do; mixed precision inside a hot loop that forces a conversion per iteration. Vectorization is not always the right answer; the choice must be deliberate, and a benchmark wins the argument.
- Unbounded work from unbounded input. A scan that processes a whole set synchronously without yielding; a decode that loads the whole payload before streaming; an analysis whose runtime grows worse than linearly with input length; a layout that recomputes from scratch on every change.
- Query and index efficiency. A query that scans the whole set when an index would do; a filter that re-realizes a lazy sequence on every access; a lookup that walks a list when a set or map would do; a sort or projection recomputed when the input has not changed.
- Waste in a render or diff pipeline. A per-frame allocation in a diff path; a uniform or buffer update that re-uploads static data; a descriptor or command buffer rebuilt when a single binding changed.
- Throughput on a scan or batch path. A scan that reads the whole payload to compute a value the header would yield; a batch that reworks items whose input has not changed (a content hash is the gate); a batch that holds a shared lock for its whole duration.
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.
- 2d ago First seen · 94 lines · 30 tokens per session scan A b3b1a9926fa7
check-performance is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 30 tokens to every session and 923 once invoked, about $0.0002 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.
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…