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 dominikwozniak/dw-solo-skills --skill dw-unslopgit clone --depth 1 https://github.com/dominikwozniak/dw-solo-skillsWrote 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/dominikwozniak/dw-solo-skills/dw-unslop)<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.
<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>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 | $0.00051 | $0.01174 |
| Opus 5.5 | $0.00020 | $0.00470 |
| Sonnet 5.5 | $0.00010 | $0.00235 |
| Haiku 4.5 | $0.00005 | $0.00117 |
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 1mo 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 — 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:
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.
- 1mo ago Changed · +2 lines e61411783f22
- 2mo ago Changed c6fe9919ab93
- 2mo ago First seen · 89 lines · 51 tokens per session scan A 21630191fa08
dw-unslop is a skill published in the GitHub repository dominikwozniak/dw-solo-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,174 once invoked, about $0.0002 per session on Opus 5.5. 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
brainstorming
Structured brainstorming for Symfony projects - explore requirements, identify components, and plan architecture collaboratively.
runner-selection
Select and configure the appropriate command runner based on Docker Compose standard, Symfony Docker (FrankenPHP), or host environment.
using-symfony-superpowers
Entry point for Symfony Superpowers - lightweight workflow guidance and command map.
daily-workflow
Daily development workflow for Symfony projects including common tasks, debugging, and productivity tips.
executing-plans
Methodically execute implementation plans with a TDD approach, incremental commits, and continuous validation.
writing-plans
Create structured implementation plans for Symfony features with clear steps, dependencies, and acceptance criteria.