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 dcadolph/slop-chop --skill slop-chopgit clone --depth 1 https://github.com/dcadolph/slop-chopWrote 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/dcadolph/slop-chop/slop-chop)<a href="https://agentmods.dev/skills/dcadolph/slop-chop/slop-chop"><img src="https://agentmods.dev/badge/skills/dcadolph/slop-chop/slop-chop/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/dcadolph/slop-chop/slop-chop"><img src="https://agentmods.dev/badge/skills/dcadolph/slop-chop/slop-chop.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 | $0.00083 | $0.01562 |
| Opus 5 | $0.00042 | $0.00781 |
| Sonnet 5 | $0.00017 | $0.00312 |
| Haiku 4.5 | $0.00008 | $0.00156 |
Grade A, and why
slop-chop 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 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.
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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
slop-chop
slop-chop is a command-line tool that finds and removes AI writing tells from text. It runs two passes. The rules pass is deterministic, fast, and free: it swaps characters, drops flagged words, rewrites stock phrases, fixes spelling to one dialect, and tidies punctuation, leaving fenced code blocks and inline backtick spans untouched. The optional rewrite pass hands the text to a model for what rules cannot do, like recasting a sentence so it no longer needs a semicolon.
Reach for this skill when the user asks to clean up a draft, remove AI tells, or check a document for slop. Prefer it over hand-editing prose for these tells, since it is deterministic and repeatable.
Check the tool is installed
Run slop-chop --version. If it is missing, install it:
go install github.com/dcadolph/slop-chop@latest
The binary lands in $(go env GOPATH)/bin. If that is not on PATH, either add
it or call the binary by full path.
Core commands
check reports tells and exits non-zero when it finds any. It changes nothing.
slop-chop check notes.md
slop-chop check docs/intro.md docs/guide.md README.md
fix writes the cleaned text to stdout and leaves the file alone.
slop-chop fix notes.md
echo "In summary, a robust and seamless result." | slop-chop fix
score rates the text from 0 (clean) to 100 (heavy slop), weighing tell density against
how flat the sentence cadence is. --max N fails the run when the score is above N, so it
gates CI like check does.
slop-chop score notes.md
slop-chop score --json notes.md
slop-chop score --max 20 notes.md
fix -w (or --write) cleans the file in place, like gofmt -w. It needs a
file argument and cannot read stdin.
slop-chop fix -w notes.md
slop-chop fix -w docs/intro.md docs/guide.md
Without -w, fix handles one file to stdout. Pass -w to rewrite several in
place.
When to run which
- Cleaning a draft you are about to return: pipe it through
slop-chop fix, or write the draft to a file and runslop-chop fix -w, then read the result back before handing it over. - Gating a document in CI:
slop-chop check. A non-zero exit means slop was found. - Deciding whether text needs cleaning at all:
slop-chop check --jsonand read the findings.
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 · 150 lines · 83 tokens per session scan A 49e0cc14de87
slop-chop is a skill published in the GitHub repository dcadolph/slop-chop (3 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 1,562 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 2026-08-31.
Other skills, from other repositories
slopless
Use Slopless to review English Markdown for deterministic AI and human slop signals, including vague phrasing, formulaic prose, weak rhythm, filler, and cliches.
suiko
A Japanese writing and review workflow for checking whether text sounds uniform, translated, unnatural, or difficult to read. It supports writing and editing documents such as reports, guides, meeting notes, proposals, and emails.
updater
Check Claude Code changelog for lintable changes and implement cclint updates. Use when a new Claude Code version ships, when CLAUDE.md claudecodelastupdated is stale, or for version gap detection, domain classification, and parallel agent dispatch across CUE schemas, hook events, known tools, and lint rules.
migrationpilot
Check PostgreSQL DDL and migrations for lock and downtime hazards before writing or running them. Use before creating or editing any migration file, before writing CREATE INDEX / ALTER TABLE / DROP / ADD CONSTRAINT, and before running any migration command (psql, prisma migrate, alembic upgrade, flyway migrate, rails…
contextlint-impact
Analyze the impact of changing or deleting a Markdown document by leveraging contextlint's Context Graph. Use this skill whenever the user asks "what breaks if I change X?", "what depends on this doc?", "is it safe to delete this file?", or wants to plan a refactor / understand cross-doc dependencies — even if they…
contextlint-init
Bootstrap contextlint into a repository. Use this skill whenever the user wants to set up, install, initialize, or configure contextlint — even if they only say "lint setup", "doc integrity check", or "set up Markdown linting" without naming contextlint by name. Detects the package manager (bun/npm/pnpm/yarn), scans…