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/validategit 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 | $0.00187 |
| Opus 5 | $0.00009 | $0.00093 |
| Sonnet 5 | $0.00004 | $0.00037 |
| Haiku 4.5 | $0.00002 | $0.00019 |
Grade A, and why
validate 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
Validate the OpenAPI/Swagger spec at $ARGUMENTS by running the kubb validate CLI in the
terminal (ask for the path or URL if empty).
-
Run validation:
npx kubb validate <spec>The input accepts a local path or a URL.
-
On success, confirm the spec is valid and offer to run
/kubb:initor/kubb:generate. -
On failure, report the validation errors clearly and, where possible, point at the offending part of the spec and suggest a fix.
Validation needs @kubb/adapter-oas. If the command reports it is missing, tell the user to
install it.
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 · 22 lines · 18 tokens per session scan A bd5082f4069b
validate 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 187 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.