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.
git clone --depth 1 https://github.com/AgriciDaniel/anti-slopWrote 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/plugins/agricidaniel/anti-slop/anti-slop-plugin)<a href="https://agentmods.dev/plugins/agricidaniel/anti-slop/anti-slop-plugin"><img src="https://agentmods.dev/badge/plugins/agricidaniel/anti-slop/anti-slop-plugin.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
anti-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 8d 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.
What it actually says
{
"name": "anti-slop",
"version": "0.1.0",
"description": "Detect and repair AI slop in prose, code, documentation, commits and agent output. Reports defects, never authorship. Runs deterministic scanners for vendor residue, placeholders, citations and packages, then structural procedures (deletion, inversion, stranger, attribution, load-bearing) that each emit a verifiable artifact. Stylistic markers are evidence-tiered and route to structural tests instead of failing on their own.",
"author": {
"name": "Daniel Agrici",
"url": "https://github.com/AgriciDaniel"
},
"homepage": "https://github.com/AgriciDaniel/anti-slop",
"repository": "https://github.com/AgriciDaniel/anti-slop",
"license": "Apache-2.0 AND CC-BY-SA-4.0 AND CC-BY-4.0",
"keywords": [
"anti-slop",
"ai-slop",
"content-quality",
"code-review",
"citation-verification",
"hallucinated-packages",
"vendor-residue",
"editorial-review",
"structural-tests",
"false-positive-control"
],
"allowed-tools": [
"Read",
"Grep",
"Glob",
"Bash",
"Write",
"Edit",
"WebFetch"
],
"_comment_allowed_tools": "claude plugin validate --strict rejects allowed-tools as unrecognised. It is retained because the Brainstein rubric item C7.3 requires a declared tool list, and it is inert at load time either way. Remove it if strict validation becomes a release gate.",
"_comment_license": "Compound by necessity. Code is Apache-2.0. The marker taxonomies under references/ adapt Wikipedia's Signs of AI writing and are CC-BY-SA-4.0, which is copyleft and cannot be relicensed. Other prose is CC-BY-4.0. See LICENSE and NOTICE in this directory."
}
What it installs
The manifest is a name and a version. 5 skills, 2 agents, 1 hook travel with it, and installing the plugin installs all of them — 1,086 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json 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.
- 8d ago First seen · 36 lines scan A f2e79b052cdd
anti-slop is a plugin published in the GitHub repository AgriciDaniel/anti-slop (45 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
procoder
A harness that gives AI coders the tools and skills to work like a senior developer. All nine domains shipped: security, best practices, maintainability, performance, documentation, clean code, CI/CD, DevOps, GitOps — plus the code index. Hooks hand the agent results; the agent stays in control.
argot
A guardrail that flags code foreign to a repo's own patterns — learned from git history. Bundles the argot-setup, argot-refresh, argot-check, argot-review-pr, argot-setup-ci, argot-write-rule, and argot-suggest-rules skills, the argot MCP server, and an opt-in, non-blocking pre-write guardrail hook.
skill-reviewer
Use when reviewing a Claude Code skill, auditing skill quality before publish, or asking "is this skill any good?". Produces structured reports with file:line citations, severity-rated findings cards, and an optional second-opinion pass. Lens variants: full (default), safety, discoverability, architecture…
dev-workflow
Spec-driven workflow with two independent cross-model review gates, an append-only hardening ledger with an escalation ladder, and repo-enforced quality. Requires the superpowers plugin.
hi-vibe
Vibe-coding seatbelt for Claude Code — doc automation (CLAUDE.md/MODULE.md/handover/CHANGELOG) + AI discipline (root-cause first, no unfounded claims) + machine enforcement (ruff/eslint/import cycles).
guardsman
Right-sized code, verified before it ships. Risk-tiered engineering judgment for AI coding agents: convention detection, blast-radius tiers, mandatory verification, and a scannable logbook for deliberate shortcuts.