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 agentmods add skills/christiangalsterer/documentation-plugin/remove-ai-slopnpx skills add christiangalsterer/documentation-plugin --skill remove-ai-slopgit clone --depth 1 https://github.com/christiangalsterer/documentation-pluginWrote 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/christiangalsterer/documentation-plugin/remove-ai-slop)<a href="https://agentmods.dev/skills/christiangalsterer/documentation-plugin/remove-ai-slop"><img src="https://agentmods.dev/badge/skills/christiangalsterer/documentation-plugin/remove-ai-slop.svg" alt="Measured on agentmods" 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 | $0.00143 | $0.02200 |
| Opus 5 | $0.00072 | $0.01100 |
| Sonnet 5 | $0.00029 | $0.00440 |
| Haiku 4.5 | $0.00014 | $0.00220 |
Grade A, and why
remove-ai-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 5d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remove AI Slop
Identify and remove AI-slop: the filler, hedging, marketing, and jargon phrases that AI text generators lean on, the structural tells they use to manufacture insight, plus em-dash overuse. Output is cleaner prose with the meaning, facts, and technical terms intact.
This skill is a reviewer/cleaner, not a writer. It edits what is there; it does not invent content or restructure the document.
It covers two kinds of slop:
- Word-level (words and phrases) — see references/phrases.md.
- Structural (constructions and rhythm) — see references/structures.md.
Workflow
-
Identify the setting. Determine the input: a file on disk to edit in place, or inline prose to return cleaned. If you write to a
.mdfile, never wrap the result in a code fence — the file content IS markdown. -
Scan the text. Flag every match of the categories below. Record the exact location (line or sentence), the current phrase, and a proposed replacement.
-
Report before editing (unless the user asked for auto-fix). Present findings as a numbered table where each entry gets a number starting at 1:
# Location Phrase Suggested fix Let the user accept or reject findings before you apply changes.
-
Apply the selected fixes. The user picks which findings to fix by number. Keep the meaning, facts, and technical terms intact.
Selecting findings. Selection is 1-based and can be a single number, a comma-separated list, a range, or any combination:
- Single:
3 - List:
1,2,5 - Range:
1-3 - Combined:
1-3,5,7-8
Whitespace after commas is allowed and ignored (
1, 3→ findings 1 and 3). An out-of-range number is not an error in the whole selection — apply the valid findings and report the ones that don't exist. Apply only what the user selected; leave the rest untouched for a later pass. - Single:
-
Re-verify against the validation checklist at the bottom, fix any remaining violations, then present the result.
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.
- 5d ago First seen · 180 lines · 143 tokens per session scan A 3afbf1290005
remove-ai-slop is a skill published in the GitHub repository christiangalsterer/documentation-plugin (1 stars, last pushed 10d ago), licensed MIT. It adds 143 tokens to every session and 2,200 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
recursive-decomposition
Handle tasks that exceed the context window by decomposing them: size and filter the input, chunk it, run recursive sub-agents on independent parts, verify on small windows, and synthesise programmatically, following the Recursive Language Models (RLM) research by Zhang, Kraska and Khattab (2025). Use when a task…
math-unicode
Use when a response needs mathematical notation (equations, filters, set-builder notation, statistics, calculus, linear algebra, logic, ratios, drops, counts) and the output goes to a terminal or TUI that cannot render LaTeX: Claude Code, Codex CLI, SSH and tmux sessions, CI logs. Load it before composing, including…
save
Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.
test-driven-development
Strict red-green-refactor TDD workflow for implementing features, fixing bugs, or changing behavior in Rails applications. Enforces the discipline of writing a failing test before any production code. Use whenever you want to implement with TDD — whether a new feature, a bugfix, a refactor, or any behavior change.
extensions
Report which extensions the connected NeatContext context expects, and whether this machine provides them. Use when the user asks what a context can reach, why an extension tool is missing, or how to connect one here.
git-commit
Turn the working changes into one or more atomic commits with well-written messages. Use whenever the user runs /git-commit or asks to commit their work, wrap up a feature, or "commit what I have.".