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/qagit 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/qa)<a href="https://agentmods.dev/commands/isaacsight/kernel/qa"><img src="https://agentmods.dev/badge/commands/isaacsight/kernel/qa.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 | $0.00000 | $0.00341 |
| Opus 5 | $0.00000 | $0.00170 |
| Sonnet 5 | $0.00000 | $0.00068 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
qa 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 yesterday.
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 full QA pass on the Kernel platform.
You are the QA Agent. Read .claude/agents/qa.md for your full protocol.
Steps:
- Load memory — Call
agent_memory_readforqaagent - Type check — Run
npx tsc --noEmit. If errors, report them as P0 and STOP. - Build — Run
npm run build. If fails, report as P0 and STOP. - Screenshot key screens — Use Playwright MCP to navigate to the live site and take snapshots of:
- Home / gate screen
- Chat with messages (if authenticated)
- Goals panel
- Briefings page
- Dark mode toggle
- Mobile viewport (resize to 375x812)
- Baseline comparison — Run
kernel_snapshotfor each screen - Bug report — For each issue found, report: Severity (P0/P1/P2), Screen, Steps, Expected, Actual
- Save findings — Call
agent_memory_writeforqawith findings - Handoff — If any issue crosses into design (Rubin violations), security (auth issues), or performance (slow loads), call
team_handoffto the relevant agent
Report format:
# QA Report — [date]
## Pre-flight
- Type check: PASS/FAIL
- Build: PASS/FAIL
## Screens Tested
[list each screen with status]
## Bugs Found
[P0/P1/P2 bugs with details]
## 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.
- yesterday First seen · 38 lines · 0 tokens per session scan A ba678f439d94
qa is a command published in the GitHub repository isaacsight/kernel (16 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 341 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
ralph-loop
/ralph-loop - Verify work was done correctly before marking complete.
mobile-check
You are invoking the mobile-check skill - comprehensive mobile viewport verification using Playwright MCP.
verify
You are invoking the verify skill - comprehensive verification following Boris Cherny's pattern.
test
You are testing a feature using Playwright MCP to verify it works.
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.