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 skills add holoviz-dev/holoviz-skills --skill deslopgit clone --depth 1 https://github.com/holoviz-dev/holoviz-skillsWrote 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/holoviz-dev/holoviz-skills/deslop)<a href="https://agentmods.dev/skills/holoviz-dev/holoviz-skills/deslop"><img src="https://agentmods.dev/badge/skills/holoviz-dev/holoviz-skills/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/holoviz-dev/holoviz-skills/deslop"><img src="https://agentmods.dev/badge/skills/holoviz-dev/holoviz-skills/deslop.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.01117 |
| Opus 5 | $0.00030 | $0.00558 |
| Sonnet 5 | $0.00012 | $0.00223 |
| Haiku 4.5 | $0.00006 | $0.00112 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deslop
Remove the recognisable machinery of LLM prose from a piece of writing without changing what it says.
Two failure modes to avoid, in order of severity:
- Changing the meaning. The point is to delete the performance, not the content. If a slop pattern is wrapped around a real claim, keep the claim and drop the wrapper.
- Trading one tic for another. A rewrite that swaps "here's the thing" for "the reality is" has done nothing. Prefer deletion over substitution.
Workflow
1. Identify the target. A file path, a range in a file, or a draft sitting in the conversation. If the user says "deslop this" with no target, use the most recent substantial prose in the conversation. If the target is ambiguous between two candidates, ask.
2. Read it in full. You cannot judge whether a sentence is load-bearing from a grep hit. Read the whole document before touching anything.
3. Scan mechanically.
python3 scripts/deslop_scan.py <file>
Flags: --colon-triple and --em-dash enable two patterns that are off by default because they are noisy in technical writing. --json for machine-readable output. Pass - to read stdin, which is how you scan a draft that only exists in the conversation:
python3 scripts/deslop_scan.py - <<'EOF'
<draft text>
EOF
The scanner is a starting point, not the specification. It has false positives (a legitimate "no X, no Y" in quoted dialogue) and it cannot see the patterns that need judgment (a paragraph that gestures at profundity without tripping any regex). Read references/patterns.md for the full catalogue, including the ones no regex catches.
4. Rewrite. Apply references/patterns.md hit by hit, then reread the whole thing for the patterns the scanner missed. Use Edit for files. For a conversation draft, output the rewritten text.
5. Verify. Re-run the scanner on the result. Every remaining hit needs a reason: quoted material, a false positive, or an intentional choice you flag to the user.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 67 lines · 61 tokens per session scan A 293667ba9ecc
deslop is a skill published in the GitHub repository holoviz-dev/holoviz-skills (5 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 61 tokens to every session and 1,117 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 2026-09-09.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…