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 ckorhonen/swe-skills --skill performance-huntgit clone --depth 1 https://github.com/ckorhonen/swe-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/ckorhonen/swe-skills/performance-hunt)<a href="https://agentmods.dev/skills/ckorhonen/swe-skills/performance-hunt"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/performance-hunt/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/ckorhonen/swe-skills/performance-hunt"><img src="https://agentmods.dev/badge/skills/ckorhonen/swe-skills/performance-hunt.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 | $0.00115 | $0.01435 |
| Opus 5 | $0.00057 | $0.00718 |
| Sonnet 5 | $0.00023 | $0.00287 |
| Haiku 4.5 | $0.00012 | $0.00144 |
Grade A, and why
swe:performance-hunt 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Performance Hunt
What This Skill Does
Use this skill to identify performance bottlenecks conservatively and turn them into a small, reviewable backlog.
The goal is to separate:
- measured bottlenecks
- high-confidence hotspots supported by repo evidence
- weak suspicions that do not yet justify optimization work
The output should be a ranked set of bottlenecks plus the smallest next experiment or fix for each item that clears the evidence bar.
When To Use
Use this skill when the user wants to:
- find performance bottlenecks in a service, job, page, query path, or repo
- understand why a specific flow is slow
- audit recent performance regressions with concrete evidence
- rank hot paths before starting optimization work
- run a recurring performance review over time
Do Not Use
Do not use this skill for:
- live incident response or active outage triage
- generic observability coverage audits
- broad cleanup or refactor planning with no performance target
- speculative micro-optimization with no measured user or system impact
- architecture rewrites that are not justified by bottleneck evidence
Inputs To Confirm
Confirm or infer:
- repository, service, or package scope
- target flow, workload, or endpoint
- primary metric of interest, such as latency, throughput, memory, startup, or bundle size
- available evidence sources such as profiles, traces, benchmarks, or query plans
- whether the user wants a report-only pass or a small optimization backlog
- any guardrails around risky changes or expensive tests
If the request is too broad, narrow it to one flow and one metric before doing deep analysis.
Evidence Sources
Strong evidence includes:
- profiler output or flamegraphs
- targeted benchmarks
- load-test results
- query plans or database timing data
- frontend bundle analysis or render timing output
- traces or metrics tied to the scoped flow
- recent regression data from CI or performance tests
Useful repo evidence includes:
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 · 232 lines · 115 tokens per session scan A dc6c8dba2884
swe:performance-hunt is a skill published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 1,435 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
postmortem
Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.
ai-diagnostic
A diagnostic framework that examines a problem across technology, processes, people, and business causes.
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
azure-mcp-observability
The read-only observability half of the azure-mcp connector — the monitor, resourcehealth, applens, and advisor namespaces: Azure Monitor metrics, Log Analytics KQL, alert-rule state, platform health states, AppLens detectors, and Advisor recommendation categories, plus the degraded-resource investigation order.
launchworthy
Production readiness audit that turns a demo into a real product. Built for apps shipped fast with AI coding tools (Lovable, Bolt, v0, Cursor, Claude Code). Auto-detects your stack and audits 5 domains (Frontend, Backend & Data, Auth & Security, Infrastructure, Operations), then produces a scored scorecard and a…