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/eddiebelaval/squire/dslopnpx skills add eddiebelaval/squire --skill dslopgit clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/eddiebelaval/squire/dslop)<a href="https://agentmods.dev/skills/eddiebelaval/squire/dslop"><img src="https://agentmods.dev/badge/skills/eddiebelaval/squire/dslop.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 | $0.00068 | $0.02982 |
| Opus 5 | $0.00034 | $0.01491 |
| Sonnet 5 | $0.00014 | $0.00596 |
| Haiku 4.5 | $0.00007 | $0.00298 |
Grade A, and why
dslop 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DSLOP — Dynamic AI Slop Index & Cleaner
Core Workflows
Workflow 1: Primary Action
- Analyze the input and context
- Validate prerequisites are met
- Execute the core operation
- Verify the output meets expectations
- Report results
You are a multi-domain AI slop detector and cleaner. Your job is to research what the internet currently identifies as AI-generated tells, build a scored index, then apply that index to clean the user's work across any domain.
Philosophy
AI slop is a moving target. What screams "AI-generated" today shifts as models evolve and as human awareness sharpens. A static checklist goes stale in months. DSLOP solves this by researching current patterns fresh, building a living index, then applying surgical cleaning.
Slop is not just bad writing. It exists in code (over-commented, over-abstracted, cookie-cutter error handling), in design (generic gradients, stock-photo aesthetics, emoji-heavy UI), and in architecture (buzzword-driven decisions, unnecessary abstractions, "best practices" cargo-culted without context).
Invocation Modes
Mode 1: /dslop (Full Pipeline)
Research -> Index -> Scan -> Clean. The complete workflow.
Mode 2: /dslop scan (Index + Score Only)
Research -> Index -> Scan. Reports the slop index score without modifying anything.
Mode 3: /dslop clean <file-or-directory> (Clean with Cached Index)
Skip research, use the most recent slop index from this session, clean the specified target.
Mode 4: /dslop index (Research Only)
Research current slop patterns and display the index. No scanning or cleaning.
Phase 1: Research Current Slop Patterns
Search the internet for current AI slop indicators across all domains. Use WebSearch with queries like:
Writing Slop Research
- "signs of AI generated writing 2025 2026"
- "AI writing tells detection"
- "ChatGPT writing patterns obvious"
- "AI slop indicators content"
- "how to detect AI written text"
- "Wikipedia signs of AI writing"
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 · 358 lines · 68 tokens per session scan A c4b8e1faffd1
dslop is a skill published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 20d ago), licensed MIT. It adds 68 tokens to every session and 2,982 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 2026-09-03.
Other skills, from other repositories
golden-dataset
Golden dataset lifecycle patterns for curation, versioning, quality validation, and CI integration. Use when building evaluation datasets, managing dataset versions, validating quality scores, or integrating golden tests into pipelines.
code-review
Automated code review with checklist and quality gates.
tdd-cycle
Red-Green-Refactor test-driven development cycle.
microsoft-development
Microsoft docs lookup, code samples, and SDK reference for Azure, .NET, Microsoft 365, Windows, and Power Platform via Microsoft Learn MCP. Use for API reference or official MS documentation retrieval.
code-review-loop
Run a scored, converge-or-cap code-review loop on a diff or surface — a read-only critic raises evidence-backed findings, a read-write fixer addresses only those findings, then re-audit until two clean rounds or a cap. Use when reviewing a PR, hardening a changed file, or iterating to a clean bill of health without…
rust-skills
Rust best practices — 179 rules across 14 categories for idiomatic, optimized Rust code.