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/sembraniteam/claude-plugins/bottleneck-patternsnpx skills add sembraniteam/claude-plugins --skill bottleneck-patternsgit clone --depth 1 https://github.com/sembraniteam/claude-pluginsWhat 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 | $0.00122 | $0.00786 |
| Opus 5 | $0.00061 | $0.00393 |
| Sonnet 5 | $0.00024 | $0.00157 |
| Haiku 4.5 | $0.00012 | $0.00079 |
Grade A, and why
bottleneck-patterns 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bottleneck Patterns
Performance Bottleneck Patterns
Identify which domain matches the symptom, then apply the corresponding pattern. For the full symptom → pattern → fix lookup tables, see references/bottleneck-lookup.md.
Domain Quick Reference
Response Time: Tail latency (p99 >> p50), throughput ceiling, cold-path slowness, periodic spikes
Web: Render-blocking resources, large JS bundles, layout thrashing, missing CDN, high INP
API/Backend: N+1 queries, missing indexes, connection pool exhaustion, synchronous I/O, over-fetching
Memory: Monotonic heap growth (leak), burst allocation GC churn, premature promotion, unbounded cache
CPU: Busy-wait loops, hot codec (serialization), uncached regex, lock contention
Mobile (Android): ANR on main thread, UI jank, overdraw, WakeLock abuse, battery drain from background work
Mobile (iOS): Main thread I/O, deep autolayout graph, retain cycles, Core Data on main thread
Mobile (Flutter): Expensive build() methods, shader compilation jank, large isolate messages, heavy list cells
Networking: Chatty API, missing compression, no connection reuse, oversized images, sequential loading
Database: Missing indexes (EXPLAIN ANALYZE first — parse PostgreSQL JSON output deterministically with the profiler-analysis skill's scripts/parse-profiler.py --format pg-explain), SELECT *, missing composite index, ORM over-fetching
Diagnostic Approach
- Match the symptom to a domain from the quick reference above
- Look up the specific pattern and fix in
references/bottleneck-lookup.md - Confirm with data before implementing: run
EXPLAIN ANALYZE, attach a profiler, or measure with a benchmark — for.cpuprofile/pprof -top/EXPLAIN ANALYZE JSONspecifically, useprofiler-analysis's parser script rather than reading raw output by eye - Apply the
impact-matrixskill to prioritize multiple findings
Cross-Domain Signals
Some symptoms span multiple domains — check these cross-cutting patterns first:
What ships with it
1 file 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.
- 2d ago First seen · 56 lines · 122 tokens per session scan A 251f45aa7219
bottleneck-patterns is a skill published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 29d ago), licensed MIT. It adds 122 tokens to every session and 786 once invoked, about $0.0006 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…