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 matteotitta/genesys-skills --skill why-slowgit clone --depth 1 https://github.com/matteotitta/genesys-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/matteotitta/genesys-skills/why-slow)<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/why-slow"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/why-slow/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/matteotitta/genesys-skills/why-slow"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/why-slow.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 | $0.00093 | $0.01316 |
| Opus 5 | $0.00046 | $0.00658 |
| Sonnet 5 | $0.00019 | $0.00263 |
| Haiku 4.5 | $0.00009 | $0.00132 |
Grade B, and why
why-slow scanned grade B with 1 finding 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 11d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
tail -10.claude/automation/sync-pull/startup-timing.log How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/why-slow — in-session perf diagnostic
When the user says "why is this slow" or invokes /why-slow, run the four checks below in parallel and emit a focused report. Goal: identify the top suspect in <30 lines so the user knows whether to restart, kill a process, or rephrase the query.
Checks (run all four in parallel via Bash)
1. Recent startup-timing log (last 10 entries)
tail -10.claude/automation/sync-pull/startup-timing.log
Look for: rising parent_age values across recent sessions (cold-start getting slower) OR a row where worktrees count spiked.
2. Current MCP processes
ps aux | grep -E "(mcp|claude.*node)" | grep -v grep | head -15
Look for: any process with high CPU% (wedged), or duplicate processes (failed handshake retrying), or processes from MCPs the user no longer uses.
3. Latest sync-pull debug log (tail)
tail -30.claude/automation/sync-pull/session-start.debug.log
Look for: timeout errors ("timeout after 10s"), gdrive/notion error messages, OAuth failures.
4. Worktree count + size
git worktree list | grep -c worktrees/
du -sh.claude/worktrees/
Look for: count >20 or size >2GB (run the worktree-cleanup runbook).
Report format (≤30 lines)
=== /why-slow diagnostic — {timestamp} ===
TOP SUSPECT: {one of: search-domain bloat | wedged MCP | OAuth-expired MCP | slow hook | no obvious slowness}
Evidence:
- {bullet 1 from the relevant check}
- {bullet 2}
- {bullet 3}
Recommended action:
- {one specific command or change}
Other observations:
- worktrees={N} ({GREEN if ≤15, YELLOW if 16-25, RED if >25})
- always-on MCPs={N} (target ≤14 per mcp-on-demand.md)
- last sync-pull: {status from debug log}
Top-suspect heuristics (in priority order)
| Symptom | Top suspect | Action |
|---|---|---|
Recent sessions show parent_age >10s |
Slow MCP handshake | Read.claude/rules/mcp-on-demand.md; demote a B-tier MCP |
| MCP process at >100% CPU | Wedged MCP | kill -9 <pid> and the next tool call will respawn it fresh |
sync-pull log shows invalid_grant |
OAuth-expired MCP | Run the relevant recovery (see reference_gdrive_oauth_reauth.md, reference_xero_mcp_refresh.md) |
| Worktree count >25 | Search-domain bloat | Run worktree-cleanup runbook |
| All checks clean but tool calls slow | Bridge latency (/remote-control) or genuinely large search | Try the same query in CLI directly (not web); scope search to specific paths |
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.
- 11d ago First seen · 121 lines · 93 tokens per session scan B c105678d6c85
why-slow is a skill published in the GitHub repository matteotitta/genesys-skills (36 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,316 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gingiris-b2b-growth
🇺🇸 B2B SaaS Growth — PLG vs SLG Playbook — Diagnose whether your problem is distribution, pricing, or PMF. PLG/SLG selection by ACV and sales cycle, the 5-stage path from $0 to $10M ARR, NRR discipline, affiliate & channel motion, enterprise tiering. Built from HeyGen, Deel, Vercel, Supabase, Snowflake patterns.…
gr-b2b-growth
A guide to growing a business-to-business software product from early user research to large-scale sales. B2B software is sold to companies rather than individual consumers.
go-to-market-playbook
A reusable Go-to-Market strategy template for both B2B and B2C launches. Covers positioning, messaging, ICP definition, channel selection, and competitive analysis frameworks. By @WeiYipei.
email-infra-bounce-audit
Audit a bounce or blacklist problem to root cause and produce a full bounce report. Use for pulling replies via the EmailBison MCP/API, working around the broken type=bounced filter, stripping auto-replies, classifying bounces (Hard/Soft/Block) by SMTP/DSN code, running the neutral-copy test, and tracing the cause to…
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.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.