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 ironbee-ai/ironbee-devtools-skills --skill performance-auditgit clone --depth 1 https://github.com/ironbee-ai/ironbee-devtools-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/ironbee-ai/ironbee-devtools-skills/performance-audit)<a href="https://agentmods.dev/skills/ironbee-ai/ironbee-devtools-skills/performance-audit"><img src="https://agentmods.dev/badge/skills/ironbee-ai/ironbee-devtools-skills/performance-audit/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/ironbee-ai/ironbee-devtools-skills/performance-audit"><img src="https://agentmods.dev/badge/skills/ironbee-ai/ironbee-devtools-skills/performance-audit.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 | $0.00060 | $0.01118 |
| Opus 5 | $0.00030 | $0.00559 |
| Sonnet 5 | $0.00012 | $0.00224 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
performance-audit 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 9d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Audit Skill
Analyze web page performance using Web Vitals and network timing metrics.
When to Use
This skill activates when:
- User asks about page performance or speed
- User wants to optimize load times
- User mentions slow page, slow API, or poor user experience
- User needs Core Web Vitals metrics
- User asks about backend bottlenecks or TTFB
- User asks about SEO performance factors
Capabilities
Web Vitals Analysis
ironbee-browser-devtools-cli o11y get-web-vitals
ironbee-browser-devtools-cli --json o11y get-web-vitals
ironbee-browser-devtools-cli --json o11y get-web-vitals --wait-ms 3000
ironbee-browser-devtools-cli --json o11y get-web-vitals --include-debug
Network Performance
ironbee-browser-devtools-cli --json o11y get-http-requests
ironbee-browser-devtools-cli --json o11y get-http-requests --resource-type script
ironbee-browser-devtools-cli --json o11y get-http-requests --resource-type stylesheet
ironbee-browser-devtools-cli --json o11y get-http-requests --status '{"min":400}'
Visual Analysis
ironbee-browser-devtools-cli content take-screenshot --name "above-fold"
ironbee-browser-devtools-cli content take-screenshot --name "full-page" --full-page
Performance Thresholds
| Metric | Good | Needs Work | Poor |
|---|---|---|---|
| LCP | ≤2.5s | 2.5-4s | >4s |
| INP | ≤200ms | 200-500ms | >500ms |
| CLS | ≤0.1 | 0.1-0.25 | >0.25 |
| TTFB | ≤800ms | 800-1800ms | >1800ms |
| FCP | ≤1.8s | 1.8-3s | >3s |
Audit Workflow
SESSION="--session-id perf-audit"
# 1. Navigate to page
ironbee-browser-devtools-cli $SESSION navigation go-to --url "https://example.com"
# 2. Wait for page to settle
ironbee-browser-devtools-cli $SESSION sync wait-for-network-idle
# 3. Get Web Vitals
ironbee-browser-devtools-cli $SESSION --json o11y get-web-vitals --wait-ms 2000
# 4. Analyze network requests
ironbee-browser-devtools-cli $SESSION --json o11y get-http-requests
# 5. Check for console errors
ironbee-browser-devtools-cli $SESSION --json o11y get-console-messages --type warning
# 6. Take screenshot for reference
ironbee-browser-devtools-cli $SESSION content take-screenshot --name "performance-audit"
# 7. Cleanup
ironbee-browser-devtools-cli session delete perf-audit
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.
- 9d ago First seen · 132 lines · 60 tokens per session scan A 87dc4f29ff5b
performance-audit is a skill published in the GitHub repository ironbee-ai/ironbee-devtools-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,118 once invoked, about $0.0003 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
react-sentinel-debug
Use React-Sentinel when a task needs live browser or React runtime inspection rather than static code reading alone.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
moli-webfetch
Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…
debug-live
Guides root-cause investigations with debugging capabilities by setting breakpoints, starting a debug session, stepping through execution, inspecting variables, and tracing symptoms back to their origin. Prefer it for runtime bugs, failing tests, exceptions, crashes, hangs, wrong/null values, and unexpected output…
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.
mongodb-query-optimizer
Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query…