dw-unslop

dw-unslop is a skill for Claude Code from dominikwozniak/dw-solo-skills. It costs 51 tokens per session (1,174 once invoked), scanned A, original, MIT.

A writing pass for text that will be read by people, such as pull-request descriptions, commit messages, and release notes. It removes wording that makes text sound machine-written while keeping the author’s voice.

In plain words
What is it for?
Editing a PR body, commit body, release note, or other specified human-facing text before sharing it.
Why use it?
It helps make human-facing engineering text clearer and more natural. It does not rewrite documents intended as instructions or memory for coding agents.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Editing a PR body, commit body, release note, or other specified human-facing text before sharing it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dominikwozniak/dw-solo-skills/dw-unslop
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.

Any agent
npx skills add dominikwozniak/dw-solo-skills --skill dw-unslop
Clone the repo
git clone --depth 1 https://github.com/dominikwozniak/dw-solo-skills

Made for: Claude Code.

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 dw-unslop

README.md
[![agentmods](https://agentmods.dev/badge/skills/dominikwozniak/dw-solo-skills/dw-unslop/github.svg)](https://agentmods.dev/skills/dominikwozniak/dw-solo-skills/dw-unslop)
Your own site
<a href="https://agentmods.dev/skills/dominikwozniak/dw-solo-skills/dw-unslop"><img src="https://agentmods.dev/badge/skills/dominikwozniak/dw-solo-skills/dw-unslop/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 dw-unslop

Your own site · 80×15
<a href="https://agentmods.dev/skills/dominikwozniak/dw-solo-skills/dw-unslop"><img src="https://agentmods.dev/badge/skills/dominikwozniak/dw-solo-skills/dw-unslop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,174 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 $0.00051 $0.01174
Opus 5 $0.00026 $0.00587
Sonnet 5 $0.00010 $0.00235
Haiku 4.5 $0.00005 $0.00117

Measured 5d ago against content hash e61411783f22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dw-unslop 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 5d 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.

skills/dw-unslop/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dw-unslop — the last pass before a human reads it

The only skill here that edits wording. Everything else in the lane writes for an agent, where density is the point; this one runs over the few things a person actually reads, where the patterns that mark text as machine-written spend the reader's attention before the content gets any.

Two failures, not one. The obvious one is slop — puffery, hedging, the vocabulary. The other is over-correction: prose sanded down until it has no opinion and no rhythm, which reads as generated just as fast. Step 3 is there for the second one.

What it reads and writes

Reads whatever the argument names: empty takes the open change's PR body and the commit bodies on its branch, a path takes that file, pasted text takes itself. Writes the rewritten text — into a tracked file only after you have seen the diff — and no .ai/ artifact of its own.

It refuses, by name: any SKILL.md, AGENTS.md / CLAUDE.md, docs/agents/*, docs/decisions/*, CONTEXT.md, CHANGE.md, HANDOFF.md, .ai/backlog/*, and any ## Gotchas block. Every one of those is written for an agent rather than a person — some loaded every session, some only when a router points at them — so a sentence trimmed out of one is an instruction a later session no longer gets, and nothing is watching to notice. Name the file, give the reason in one line, stop — never counter-offer a lighter touch on the same file.

Workflow

1. Scan

Read the text against references/patterns.md: 31 numbered rules in seven groups, each written as an edit rather than a flag. Note which numbers fire — step 4 reports them.

2. Rewrite

Preserve the meaning and match the register the text was aiming at. A PR body is not an essay: the fix for puffery there is the fact the puffery stood in for, not livelier puffery. Where a rule fires but the rewrite would change what the sentence claims, leave it and say so. The claim is the author's.

3. Don't flatten it

Cutting patterns is half the job. Sterile is its own tell, so the pass has to put something back:

Read the full file on GitHub · 91 lines

Files

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.

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. 5d ago Changed · +2 lines e61411783f22
  2. 8d ago Changed c6fe9919ab93
  3. 12d ago First seen · 89 lines · 51 tokens per session scan A 21630191fa08

Subscribe to this mod's changes

dw-unslop is a skill published in the GitHub repository dominikwozniak/dw-solo-skills (2 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,174 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

self-improve

Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.

SpaiR/task-pipeline · 76 tokens

self-audit

Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.

SpaiR/task-pipeline · 52 tokens

grill

Interrogate a plan or decision one question at a time before capture, keeping a decision-plus-rationale ledger, then route to the right capture skill.

SpaiR/task-pipeline · 33 tokens

architect

Answer build-or-adopt honestly, then design one committed architecture from your own understanding of the problem — driven by ranked quality attributes, stress-tested against the field and against change, proven by a walking skeleton, its consequences confirmed by the user, committed to ARCHITECTURE.md. A command the…

donald-ada/workinggenius · 80 tokens

designer

Settle the look before the pixels — audience and context first, then the base and the delta, taste settled by looking at real states, accessibility as the floor, one design language committed to DESIGN.md as tokens with roles. A command the user types, for work with an interface someone will see; standalone, no other…

donald-ada/workinggenius · 69 tokens

errata

Correct what was written wrong — the binding line rewritten in place, the record it came from appended to and never touched, both carrying the evidence that overturned it. Use when a run, a file, or the user contradicts something already written in a work file, a plan's contract, the glossary, or the decision index…

donald-ada/workinggenius · 92 tokens