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/kubb-labs/kubb/initgit clone --depth 1 https://github.com/kubb-labs/kubbWhat 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 | $0.00018 | $0.00352 |
| Opus 5 | $0.00009 | $0.00176 |
| Sonnet 5 | $0.00004 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
init 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
Scaffold Kubb in the current project by running the kubb init CLI in the terminal. The
arguments map to its flags: an OpenAPI spec (--input), an output directory (--output), and a
comma-separated plugin list (--plugins). Read the config skill before choosing plugins.
Parsed from $ARGUMENTS (ask only for what is missing):
-
Choose plugins. Map the requested outputs to
@kubb/plugin-*packages with theconfigskill. Valid values:plugin-ts,plugin-axios,plugin-fetch,plugin-react-query,plugin-vue-query,plugin-zod,plugin-faker,plugin-msw,plugin-cypress,plugin-mcp,plugin-redoc. Default toplugin-tswhen the user is unsure. -
Run init with
--yesand the chosen values so it never prompts:npx kubb init --yes --input <input> --output <output> --plugins <comma,separated,list>This writes
kubb.config.tsand installskubbplus the selected packages (--yesalso creates apackage.jsonif the project has none). For a default setup,npx kubb init --yesworks without flags. If a config already exists, edit it by hand rather than rerunning init. -
Suggest running
/kubb:generatenext.
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 · 26 lines · 18 tokens per session scan A ba821df468f0
init is a command published in the GitHub repository kubb-labs/kubb (1,788 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 352 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
skmtc-retro-review
Aggregate SKMTC friction log entries into a review — cluster patterns, classify interventions, calculate convergence metrics, produce an action plan.
skmtc-retro
Run a SKMTC retrospective on the current session — capture friction and wins to the friction log.
CLAUDE
Command "CLAUDE" from skmtc/skmtc, covering recent activity, may 5, 2026, may 8, 2026, may 9, 2026 and may 11, 2026.
feature
Implement a multi-layer feature.
fix
Fix a small, well-scoped bug.
cflx-apply
Implement an approved OpenSpec change and keep tasks in sync.