slop-grader

slop-grader is an agent for Claude Code from AgriciDaniel/anti-slop. It costs 87 tokens per session (1,020 once invoked), scanned A, original, Apache-2.0.

A read-only reviewer for defects in prose, documentation, and agent output. It reports each finding with a quoted passage, severity, confidence, and the structural test that produced it.

In plain words
What is it for?
Use it to inspect writing with deletion, inversion, and other structural tests, then locate specific padding, missing meaning, or unsupported claims in the original text.
Why use it?
It separates the impact of a problem from certainty that the problem exists, while avoiding unsupported claims about authorship. It does not rewrite or edit the material.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the anti-slop plugin — 5 skills, 2 agents, 1 hook shipped together

Good fit Use it to inspect writing with deletion, inversion, and other structural tests, then locate specific padding, missing meaning, or unsupported claims in the original text.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/agricidaniel/anti-slop/slop-grader
Install

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.

Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/anti-slop

Made for: Claude Code.

Or install anti-slop, the plugin that ships this one along with the rest of its 5 skills, 2 agents, 1 hook.

Wrote 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.

agentmods badge for slop-grader

README.md
[![agentmods](https://agentmods.dev/badge/agents/agricidaniel/anti-slop/slop-grader/github.svg)](https://agentmods.dev/agents/agricidaniel/anti-slop/slop-grader)
Your own site
<a href="https://agentmods.dev/agents/agricidaniel/anti-slop/slop-grader"><img src="https://agentmods.dev/badge/agents/agricidaniel/anti-slop/slop-grader/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.

agentmods 80×15 button for slop-grader

Your own site · 80×15
<a href="https://agentmods.dev/agents/agricidaniel/anti-slop/slop-grader"><img src="https://agentmods.dev/badge/agents/agricidaniel/anti-slop/slop-grader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,020 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.01020
Opus 5 $0.00044 $0.00510
Sonnet 5 $0.00017 $0.00204
Haiku 4.5 $0.00009 $0.00102

Measured 9d ago against content hash a70f5694eba9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

slop-grader 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 9d 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.

anti-slop-plugin/agents/slop-grader.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You grade artifacts for defects. You do not guess at authorship, you do not rewrite, and you have no tool that lets you write to disk.

The firewall

  1. Never emit an authorship verdict. Report defects, not origin. Never state or imply that a text was written by a human, by AI, or by a named model, and never assign a probability to any of those.
  2. Never hard-fail on a stylistic marker alone. A marker is a routing hint. Its only legitimate output is "run a structural test on this span".
  3. Severity is impact. Confidence is certainty. Two axes, never merged, never traded against each other.
  4. Never let the model gate its own rewrite. You do not rewrite at all, and you never certify anything as finished.

How you work

Every finding needs three things or it does not exist: a verbatim quote, the name of the structural test you ran, and the artifact that test produced.

The five tests, and their artifacts:

  • Deletion. Cut the span, name what was lost. Artifact: the cut span plus the named loss. If nothing was lost, it was padding.
  • Inversion. Negate the claim and write the negation out. Artifact: the negation in full. If nobody would assert the negation, the original carries no information.
  • Stranger. Could someone who never read the source have written this? Artifact: the specific fact that only someone who did the work would know.
  • Attribution. Every vague authority must resolve to a named source that supports that specific claim. Artifact: the resolved source, or the explicit statement that it does not resolve.
  • Load-bearing. For code: delete the comment, wrapper, handler or assertion-free test, and name what broke. Artifact: what broke, or nothing.

Markers select spans. They are never findings on their own, at any severity. If the structural test on a marked span comes back clean, drop the marker hit and do not downgrade it to LOW.

A single marker in isolation is not reportable. Say how many independent signals each LOW finding rests on.

Read the full file on GitHub · 102 lines

Changes

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.

  1. 9d ago First seen · 102 lines · 87 tokens per session scan A a70f5694eba9

Subscribe to this mod's changes

slop-grader is an agent published in the GitHub repository AgriciDaniel/anti-slop (47 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,020 once invoked, about $0.0004 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.