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 commands/isaacsight/kernel/perfgit clone --depth 1 https://github.com/isaacsight/kernelWrote 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/commands/isaacsight/kernel/perf)<a href="https://agentmods.dev/commands/isaacsight/kernel/perf"><img src="https://agentmods.dev/badge/commands/isaacsight/kernel/perf.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00447 |
| Opus 5 | $0.00000 | $0.00224 |
| Sonnet 5 | $0.00000 | $0.00089 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
perf 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.
What it actually says
Run a performance audit on the Kernel platform.
You are the Performance Agent. Read .claude/agents/performance.md for your full protocol and budgets.
Steps:
- Load memory — Call
agent_memory_readforperformanceagent - Build with timing — Run
time npm run buildand capture build duration - Bundle sizes — After build, check
dist/assets/for JS and CSS sizes:ls -lh dist/assets/*.js dist/assets/*.cssgzip -c dist/assets/index-*.js | wc -c(gzipped JS size)gzip -c dist/assets/index-*.css | wc -c(gzipped CSS size)
- Type check timing — Run
time npx tsc --noEmit - Dependency check — Run
kernel_depsto identify outdated or bloated packages - Endpoint latency — Run
kernel_uptimeto measure API response times - Budget comparison — Compare all metrics against budgets:
- JS < 200KB gzip (critical > 300KB)
- CSS < 100KB gzip (critical > 150KB)
- Build < 30s (critical > 60s)
- Type check < 15s (critical > 30s)
- API p95 < 2s (critical > 5s)
- Save findings — Call
agent_memory_writeforperformancein "Bundle Size History" with current sizes - Handoff — If bundle bloat traces to specific deps, call
team_handofftodevops
Report format:
# Performance Report — [date]
## Bundle
- JS: XXkb gzip — PASS/FAIL
- CSS: XXkb gzip — PASS/FAIL
## Build
- Build time: XXs — PASS/FAIL
- Type check: XXs — PASS/FAIL
## API Latency
[endpoint results]
## Dependencies
[outdated/vulnerable packages]
## Verdict: PASS / FAIL
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 · 45 lines · 0 tokens per session scan A 1d059d21bb58
perf is a command published in the GitHub repository isaacsight/kernel (16 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 447 tokens. 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 2026-09-03.
Other commands, from other repositories
sync_env_from_1password
Command "sync_env_from_1password" from markmhendrickson/neotoma, covering sync environment variables from 1password, command, purpose, when to use and execution instructions.
deploy-watch
Watch a Vercel deployment until it's live, errored, or timed out. Designed to be used with /loop for hands-free monitoring.
guard
Show the latest covguard run, spend against the cap, outcome, and receipt.
AGENTS
Command "AGENTS" from binary16labs/prime-silo, covering agents, purpose, documentation hierarchy, how to document command child docs and contract.
tokenless-stats
Show Tokenless compression statistics.
env
Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.