Borrowing it
Nothing to install: this file belongs to saschb2b/okf-studio. 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/saschb2b/okf-studio/main/.agents/skills/no-slop/SKILL.mdgit clone --depth 1 https://github.com/saschb2b/okf-studioWrote 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/saschb2b/okf-studio/no-slop)<a href="https://agentmods.dev/skills/saschb2b/okf-studio/no-slop"><img src="https://agentmods.dev/badge/skills/saschb2b/okf-studio/no-slop/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/saschb2b/okf-studio/no-slop"><img src="https://agentmods.dev/badge/skills/saschb2b/okf-studio/no-slop.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 | $0.00219 | $0.02875 |
| Opus 5.5 | $0.00088 | $0.01150 |
| Sonnet 5.5 | $0.00044 | $0.00575 |
| Haiku 4.5 | $0.00022 | $0.00287 |
Grade A, and why
no-slop 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 3d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Without the Slop
The register
Target voice: a German professional writing English at C2 level. Precise, direct, structurally clean. Reserved rather than enthusiastic. This is a register, not an accent, so no Germanisms, no false friends, no grammar errors. Near-native English, just without the bubbly American default.
Most AI slop is not wrong, it is over-written and over-organized. Too warm, too balanced, too scaffolded, too eager to summarize itself. Strip that and the text gets shorter and better. The goal is prose that reads like a competent person wrote it on purpose.
Work top down
Slop lives at every scale, from the table of contents down to the word. Polishing sentences inside a structure that is itself slop is wasted work, so run the passes in order. Each pass deletes text the later passes would otherwise polish.
- Rethink the document. Reorder, merge, split, delete, and replace whole sections. The moves are below, the worked examples in structure.md.
- Rebuild the paragraphs. One topic each, point first, steps out of prose.
- Build the sentences right with the STE construction rules.
- Kill the word-level tells, including the adopted Microsoft mechanics.
- Check with the linter, then the human-only reads.
On any draft longer than a few paragraphs, a wording-only edit means the biggest pass was skipped. Make the structural moves, or state that the structure is sound and why. When writing new prose the same order applies as questions: what does the reader need, in what order, then the paragraph plan, then the sentences. When writing inside code (a comment, commit message, test name, error string), apply the same register and check the matching file under Beyond prose.
Two standing rules. Match the surrounding work (a repo's history, a doc's established voice, a mandated template); these rules sharpen writing, they do not override a house style the user follows. And when you restructure someone's draft, report the moves ("merged X into Y, dropped Z"), never silently.
What ships with it
30 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.
- CARD.manifest.json 3.5 KB
- CARD.md 4.9 KB
- CARD.md.sigstore 4.3 KB
- CARD.svg 9.8 KB
- permissions.yaml 455 B
- references/code-comments.md 4.5 KB
- references/code-strings.md 2.4 KB
- references/commits-and-prs.md 3.2 KB
- references/formatting.md 3.3 KB
- references/inclusive-and-accessible.md 4.5 KB
- references/index.md 1.9 KB
- references/log.md 7.9 KB
- references/microsoft-style.md 6.1 KB
- references/microsoft/capitalization.md 3.7 KB
- references/microsoft/grammar.md 6.4 KB
- references/microsoft/index.md 1.6 KB
- references/microsoft/numbers-and-acronyms.md 4.0 KB
- references/microsoft/procedures.md 5.6 KB
- references/microsoft/punctuation.md 8.7 KB
- references/microsoft/scannable-and-global.md 5.9 KB
- references/microsoft/word-choice.md 6.2 KB
- references/prose.md 7.8 KB
- references/ste.md 12 KB
- references/ste/dictionary.md 5.8 KB
- references/ste/index.md 1.0 KB
- references/ste/multi-word-nouns.md 2.7 KB
- references/ste/procedural-and-descriptive.md 4.0 KB
- references/ste/safety-and-word-counts.md 3.7 KB
- references/structure.md 5.0 KB
- slop-lint.mjs 13 KB runs code
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.
- 3d ago First seen · 138 lines · 219 tokens per session scan A 58e41ba30578
no-slop is a skill published in the GitHub repository saschb2b/okf-studio (47 stars, last pushed yesterday), licensed MIT. It adds 219 tokens to every session and 2,875 once invoked, about $0.0009 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 2026-10-23.
Other skills, from other repositories
okf-loom
Load this repo skill when working with Open Knowledge Format (OKF) bundles: validate, search, discover, update, render, serve the live studio, author concepts, or use the bundled OKF docs. The repo is the distribution unit; run scripts from the checkout with scripts/okf-loom.
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
potpie-resource-markdown
Use when the user asks to ingest a markdown or HTML document — an exported doc, wiki or Confluence page, web page, runbook, spec, or RFC — into Potpie so agents can search and cite it. Teaches the extraction-script flow: split on the heading tree into sections and 4k-char chunks, import with potpie resource import…
potpie-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, resolve/search/record, graph workbench reads/writes, resource (document payload) commands, and pot scope behavior.
potpie-repo-baseline
Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.