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 charlesjones-dev/claude-code-plugins-dev --skill slop-auditgit clone --depth 1 https://github.com/charlesjones-dev/claude-code-plugins-devWrote 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/charlesjones-dev/claude-code-plugins-dev/slop-audit)<a href="https://agentmods.dev/skills/charlesjones-dev/claude-code-plugins-dev/slop-audit"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/slop-audit/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/charlesjones-dev/claude-code-plugins-dev/slop-audit"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/slop-audit.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 | $0.00100 | $0.02381 |
| Opus 5.5 | $0.00040 | $0.00952 |
| Sonnet 5.5 | $0.00020 | $0.00476 |
| Haiku 4.5 | $0.00010 | $0.00238 |
Grade A, and why
slop-audit scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Legal pages against the code.** For every third party, cookie, tracker or data flow the privacy policy names, confirm the code uses it. Look for ones it misses: fonts, analytics, ad pixels, session replay, error trac How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI slop audit
Find the copy that reads as machine-written, the layouts that read as templates, and the statements that are wrong. Then give the owner a plan they can approve in one reply. The audit changes nothing; edits start only after the owner answers.
Arguments: $ARGUMENTS. Read them as scope (areas to include or skip) and, if a URL is present, the live site to check claims against. With no arguments, audit every user-facing surface in the repo.
1. Load the project's own rules first
Read whichever of these exist: CLAUDE.md, AGENTS.md, a knowledge base (docs/kb/_index.md, _global-learnings.md, and anything named voice, style, writing, brand or copy), DESIGN.md, and notes from earlier audits. Note:
- owner rules about voice and positioning: what the owner does and doesn't offer, banned words, audience;
- house-style choices that look like tells but are deliberate (heading case, bold inline headers, a brand metaphor, a design element DESIGN.md defends). These override the generic signals, so don't flag them;
- decisions from earlier audits, so you don't re-ask settled questions;
- the live URL (site config,
package.jsonhomepage,CNAME, README) if the arguments didn't give one.
Then read signals.md. It's the checklist for every step below.
2. List every user-facing surface
Make the list before reading, so the report can say exactly what it covered. Depending on the codebase:
- Web: every page and route; shared layout (header, footer, nav); components that carry copy; data files that feed cards (products, projects, case studies, testimonials, FAQs); 404 and error pages; legal pages; forms (labels, placeholders, validation, success and failure messages); transactional emails; server error text users can see.
- Metadata: meta titles and descriptions, OG and Twitter tags and images, JSON-LD,
llms.txtandllms-full.txt,manifest.json, RSS titles. - Apps: localized strings, onboarding, paywall, empty states, alerts, App Store and Play metadata (fastlane
metadata/, release notes). - Libraries and CLIs: README, docs site,
--helptext, error messages, package description.
What ships with it
1 file 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.
- 10d ago First seen · 136 lines · 100 tokens per session scan A fc6fa911f5bf
slop-audit is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (35 stars, last pushed 6d ago), licensed MIT. It adds 100 tokens to every session and 2,381 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-07.
Other skills, from other repositories
check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
write
Rewrites and polishes Chinese or English prose, technical instructions, and product copy. Use when drafting, editing, localizing, or cutting AI tone. Not for code comments or commit messages.
skill-design-lineage
Persist design documents with branch tracking, revision chains, and cross-session discovery.
pr-lens
WHAT: Draws a code change or part of a codebase as an animated architecture or data-flow diagram, on its own or in a pull request. WHEN: asked to diagram, visualise or explain a change or a system, or when a pull request should carry a diagram. KEYWORDS: PR Lens, diagram, architecture, data flow, visualise, visualize…
finalize
Pre-ship gate — runs detector, verifies brief and tokens, applies the 10-pass finish bar, ranks findings by feedback hierarchy. Use when the user wants to ship, merge, or finalize a surface and needs a verdict (READY / NOT READY / BLOCKED) before committing. Invoke when the user asks for finalize on their UI, or…
friction-log
File contributor or agent papercuts as GitHub issues labeled friction, or investigate those issues as the daily friction-log Cloud Agent. Use when you hit repo friction, when asked to log friction, or when spawned to resolve open friction issues.