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 Consensys/ask-o11y-plugin --skill analyzing-performancegit clone --depth 1 https://github.com/Consensys/ask-o11y-pluginWrote 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/consensys/ask-o11y-plugin/analyzing-performance)<a href="https://agentmods.dev/skills/consensys/ask-o11y-plugin/analyzing-performance"><img src="https://agentmods.dev/badge/skills/consensys/ask-o11y-plugin/analyzing-performance/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/consensys/ask-o11y-plugin/analyzing-performance"><img src="https://agentmods.dev/badge/skills/consensys/ask-o11y-plugin/analyzing-performance.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 | $0.00087 | $0.00696 |
| Opus 5.5 | $0.00035 | $0.00278 |
| Sonnet 5.5 | $0.00017 | $0.00139 |
| Haiku 4.5 | $0.00009 | $0.00070 |
Grade A, and why
analyzing-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 1mo 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance analysis workflow
- Establish scope — Identify the target system (service, pod, namespace, cluster) and the exact time window from the user's request. Resolve datasource UIDs once and reuse them.
- Query key metrics — CPU and memory usage vs limits, request latency percentiles (p50/p95/p99), error rates, and saturation signals (queue depth, connection pools, thread counts).
- Identify bottlenecks — Compare resource requests/limits against usage; look for throttling, OOM kills, restarts, GC pauses, and slow downstream dependencies.
- Search logs — Warnings and errors for the affected services in the same window; note recurring patterns and their frequency.
- Check traces — Use traces only when the symptom is request-level latency or failures: span durations, downstream call latency, and error spans for the affected services.
- Correlate — Align findings across signals by timestamp to separate cause from symptom (deploy markers, traffic spikes, dependency latency, config changes).
- Recommend — Rank optimization steps by expected impact and confidence, and give one verification query per recommendation.
Method shortcuts
- RED first, then USE — for request-serving services, check Rate, Errors, Duration; for resources (nodes, disks, connections), check Utilization, Saturation, Errors.
- Percentile caveats — p99 is per-request, not per-user: on 10 rps, p99 ignores ~1 in 10 seconds of traffic; a latency problem visible in p95 but not p50 means a tail subset (one AZ, one route, one pod) is affected — slice percentiles by route/instance to find it.
- Triage order — saturation before latency before errors: a saturated resource (CPU throttling, connection-pool exhaustion, disk I/O) explains downstream latency and errors; fixing the symptom query first wastes the investigation.
- Compare against baseline — diff the same window one day or one week earlier (
offset 1d) rather than judging absolute values.
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.
- 1mo ago Changed · +9 lines · +30 tokens per session 7ed4d292d317
- 1mo ago First seen · 36 lines · 57 tokens per session scan A f406d99ec1cb
analyzing-performance is a skill published in the GitHub repository Consensys/ask-o11y-plugin (42 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 696 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-07.
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.
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…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.