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 owainlewis/agent-skills --skill deslopgit clone --depth 1 https://github.com/owainlewis/agent-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/owainlewis/agent-skills/deslop)<a href="https://agentmods.dev/skills/owainlewis/agent-skills/deslop"><img src="https://agentmods.dev/badge/skills/owainlewis/agent-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/owainlewis/agent-skills/deslop"><img src="https://agentmods.dev/badge/skills/owainlewis/agent-skills/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 | $0.00070 | $0.01094 |
| Opus 5.5 | $0.00028 | $0.00438 |
| Sonnet 5.5 | $0.00014 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00109 |
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 1mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deslop
Make writing sound like it was written by a person.
Process
- Identify the point, facts, intended reader, tone, and format.
- Find the AI patterns below.
- Rewrite the affected lines. Preserve meaning and useful detail.
- Restore the writer's voice after removing the patterns.
- Read the result again. Fix anything stiff, generic, or more polished than the intended tone.
- Return the finished writing. Explain changes only when asked.
Protect the source
- Keep facts, numbers, citations, quotes, code, commands, paths, names, and technical terms accurate.
- Keep the writer's level of formality, point of view, and distinctive wording.
- Do not invent facts, sources, opinions, feelings, stories, or experience.
- Change only what improves the writing.
Restore a human voice
- Keep the writer's opinion. Do not turn it into a neutral list of pros and cons.
- Use first person when the source or requested voice uses it.
- Vary sentence length and rhythm.
- Keep specific, odd, funny, blunt, or messy details that make the writing sound like the writer.
- Prefer a concrete reaction or observation to a general statement.
- Do not force every idea into matching sections or lists.
- When the user provides no writing sample, use plain conversational English. Be direct, calm, and specific.
Remove AI patterns
Empty content
- Cut introductions and conclusions that repeat the request or answer.
- Replace claims of importance with what actually changes.
- Cut sentences that could appear unchanged in an unrelated article.
- Replace vague sources such as "experts," "reports," and "critics" with a named source or remove the claim.
- Replace formulaic challenges such as "despite these challenges" with the specific problem and result.
- Do not add praise, hype, or promotional adjectives without evidence.
Stock language
- Rewrite puffery such as "pivotal moment," "testament to," "evolving landscape," "setting the stage," "deeply rooted," and "indelible mark."
- Cut AI vocabulary such as "delve," "tapestry," "intricate," "interplay," "crucial," "vibrant," "groundbreaking," and "renowned" when a plain word says more.
- Replace "utilize" and "leverage" with "use," "facilitate" with "help," and "numerous" with "many" or a number.
- Replace "serves as," "stands as," "boasts," and "features" with "is" or "has" when that is the meaning.
- Cut filler such as "in order to," "due to the fact that," and "it is important to note that."
- Do not swap a banned word for a fancier synonym. Rewrite the thought.
What ships with it
1 file 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.
- 1mo ago First seen · 91 lines · 70 tokens per session scan A 9181c8093193
deslop is a skill published in the GitHub repository owainlewis/agent-skills (44 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 1,094 once invoked, about $0.0003 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.