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 | $0.00035 | $0.00547 |
| Sonnet 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 10d 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.
- 10d 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 19d ago), licensed MIT. It adds 70 tokens to every session and 1,094 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
x-tweet-by-conversation
Collects every tweet in an X (Twitter) conversation thread given a conversation id (root tweet id) — the focal tweet plus all replies, sub-replies, and quote chains — and returns normalized per-tweet data with text, author, engagement counts, media, hashtags, mentions, inreplyto mapping, and cursor for pagination. Use…
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
auditing-azure-active-directory-configuration
Auditing Microsoft Entra ID (Azure Active Directory) configuration to identify risky authentication policies, overly permissive role assignments, stale accounts, conditional access gaps, and guest user risks using AzureAD PowerShell, Microsoft Graph API, and ScoutSuite.
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.