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 sjarmak/coding-agent-workflows --skill slop-checkgit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWrote 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/sjarmak/coding-agent-workflows/slop-check)<a href="https://agentmods.dev/skills/sjarmak/coding-agent-workflows/slop-check"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/slop-check/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/sjarmak/coding-agent-workflows/slop-check"><img src="https://agentmods.dev/badge/skills/sjarmak/coding-agent-workflows/slop-check.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 | $0.00158 | $0.01263 |
| Opus 5.5 | $0.00063 | $0.00505 |
| Sonnet 5.5 | $0.00032 | $0.00253 |
| Haiku 4.5 | $0.00016 | $0.00126 |
Grade A, and why
slop-check 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 26d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slop & Erosion Check
A focused LLM-judge pass that scores a change the way SlopCodeBench scores agents: on Erosion (verbosity, dead branches, redundant structure that piles up as code is extended) and Verbosity (unnecessary complexity), both lower-is-better. The premise: agents rarely write wrong code — they patch their way into slop, and early design decisions compound across changes.
This is the accumulated-cruft axis, and it scans code, not prose. For correctness and reuse, use the review skill; for security, the security-review skill; for AI-writing slop in prose or docs (including READMEs), use no-ai-slop. They compose.
When to use
- After a change that extends existing code across one or more requirement shifts.
- Before opening a PR on a non-greenfield change.
- When a function/module has grown over several edits and feels heavy.
- Skip for trivial diffs (typo, one-line fix, formatting, dependency bump) — there is no erosion surface.
Phase 1: Map the surface (extended vs. greenfield)
Get the diff: git diff (or git diff HEAD with staged changes; or the files just edited if no git changes). For large diffs, write once to /tmp/slop-diff.txt and reference the path.
Split the changed code into two buckets — this drives the weighting:
- Extended surface (HIGH weight): hunks inside functions/modules that already existed. This is where erosion lives.
- Greenfield surface (normal weight): entirely new files/functions.
For the extended surface, read the whole enclosing function/module, not just the hunk — erosion is only visible against the surrounding code.
Phase 2: Judge against the rubric (the model judges, not regex)
The rubric is the catalog in the anti-slop rule (rules-reference/anti-slop.md, the SlopCodeBench 45-criterion judge, grouped). These are semantic judgments — do not grep for them; read and reason. For a large or cross-file diff, dispatch a general-purpose reviewer with a role clamp ("You are a verification agent; you did NOT write this code; actively read the enclosing modules") and the anti-slop catalog; otherwise judge directly.
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.
- 26d ago Changed ab3b899467e3
- 1mo ago Changed · +1 tokens per session 2fa2c70c4e0b
- 1mo ago First seen · 74 lines · 157 tokens per session scan A 83d2fb7c122e
slop-check is a skill published in the GitHub repository sjarmak/coding-agent-workflows (7 stars, last pushed 3d ago), licensed MIT. It adds 158 tokens to every session and 1,263 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
Agent Instruction Drift Check
Procedure for comparing an agent-facing instruction doc (AGENTS.md/CLAUDE.md-style) against the actual current code and configuration to find and flag mismatches.
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…
no-comments
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
find-simplifications
Use when asked to find or plan Cherry Studio cleanup, simplification, refactoring, dead-code removal, duplicated state removal, unnecessary APIs, speculative generality, or library replacements, especially when the result should become evidence-backed proposed Agent Notes.