Kubb is a modular code-generation framework that turns OpenAPI descriptions into type-safe TypeScript code, Zod schemas, and TanStack Query integrations. It is used by TypeScript developers to generate client code and related interfaces from API specifications. The catalogue contains extensions such as skills, commands, hooks, agents, and a plugin that support Kubb workflows.
Borrowing it
Nothing to install: this file belongs to kubb-labs/kubb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kubb-labs/kubb/main/.agents/skills/deslop/SKILL.mdgit clone --depth 1 https://github.com/kubb-labs/kubbWrote 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/kubb-labs/kubb/deslop)<a href="https://agentmods.dev/skills/kubb-labs/kubb/deslop"><img src="https://agentmods.dev/badge/skills/kubb-labs/kubb/deslop/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/kubb-labs/kubb/deslop"><img src="https://agentmods.dev/badge/skills/kubb-labs/kubb/deslop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.00455 |
| Opus 5 | $0.00028 | $0.00228 |
| Sonnet 5 | $0.00011 | $0.00091 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
deslop 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.
What it actually says
Deslop
Remove AI-generated code slop introduced in a branch so the diff reads like a human wrote it and matches the surrounding file and this repo's conventions.
When to use
- After writing or generating a batch of code, before opening a PR.
- When a diff shows the tells of AI generation: over-commenting, defensive scaffolding, or style that fights the existing file.
- Prose and user-facing markdown are out of scope. Run the
humanizerskill over those instead.
What to remove
- Comments a human would not add: restating what the code already says, or inconsistent with the comment density of the rest of the file.
- Defensive checks and
try/catchblocks abnormal for the area, especially on trusted or already-validated code paths. Thesecurityrule puts validation at trust boundaries, not in internal code. - Casts to
anyused only to bypass a type error. Fix the type instead. - Deep nesting that early returns would flatten.
- Naming, import, or export style inconsistent with the file and the
code-stylerule.
Guardrails
- Keep behavior unchanged unless you are fixing a clear bug.
- Prefer minimal, surgical edits over broad rewrites.
- Never remove a check that guards a real trust boundary or real error handling. When unsure whether a check is slop or load-bearing, leave it.
- Do not weaken types, lint rules, or tests to make the edit pass. Fix the root cause.
- After editing, run
pnpm format && pnpm lint:fixand let the tests pass. - Report a 1-3 sentence summary of what changed.
Related skills
| Skill | Use for |
|---|---|
| humanizer | Removing AI tells from prose and user-facing markdown |
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 · 44 lines · 56 tokens per session scan A a4f3943b9be7
deslop is a skill published in the GitHub repository kubb-labs/kubb (1,794 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 455 once invoked, about $0.0003 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 skills, from other repositories
skmtc-lang-typescript
The TypeScript target-language layer for Skmtc generators (@skmtc/lang-typescript): projection base factories, TsSnippet, the three register shapes, identifier kinds and the type-only import machinery, composition helpers, sanitization, TsFile render rules. Use ALONGSIDE skmtc-generator whenever a generator emits…
lathe-release
Run Lathe release validation and publishing workflows. Use when the user asks to prepare, validate, cut, tag, publish, or ship a Lathe versioned release; runs the captured pre-release regression gate before tagging.
update-skills
Create or update repository skills and instructions when major learnings are discovered during a session. Use when the user says "learn!", when a significant pattern or pitfall is identified, or when reusable domain knowledge should be captured for future sessions.
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
commit
Commit staged or unstaged changes with an AI-generated commit message that matches the repository's existing commit style. Use when the user asks to 'commit', 'commit changes', 'create a commit', 'save my work', or 'check in code'.
sync
Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase onto upstream, push current branch, publish branch, or set upstream.