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 larsboes/Axon --skill unslopgit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/unslop)<a href="https://agentmods.dev/skills/larsboes/axon/unslop"><img src="https://agentmods.dev/badge/skills/larsboes/axon/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/larsboes/axon/unslop"><img src="https://agentmods.dev/badge/skills/larsboes/axon/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 | $0.00215 | $0.02279 |
| Opus 5.5 | $0.00086 | $0.00912 |
| Sonnet 5.5 | $0.00043 | $0.00456 |
| Haiku 4.5 | $0.00021 | $0.00228 |
Grade A, and why
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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unslop
Read this first, because the most common misunderstanding sinks the whole thing.
This skill writes nothing and has no house style. It does two narrow things. It removes the specific cues that make code or an interface read as machine-made, and where the output reads as AI because nobody ever made a choice, it forces a deliberate one. Correctness, taste, and architecture stay with the person building. A guardrail is not an engineer and it is not a designer.
The trap to avoid (this is the whole point)
Every anti-slop effort fails the same way: it replaces one default with another. In UI the 2024 tell was the purple-to-blue gradient on a dark hero; the 2026 tell is warm cream, a serif display face, and a sage accent, which is the current Claude house look. In code it is the model told to "write clean code" over-correcting into defensive checks for impossible cases, a type on every local, a comment on every block, an abstraction with one caller. Trying to look senior is itself a tell.
So this skill never prescribes a palette, a font, a layout, or a pattern. Prescribing one is how a skill becomes next year's slop. A tell is an unspecified default, not a banned thing. If the user genuinely wants purple, or a broad catch at a process boundary, that is a decision and the skill leaves it alone. The only universal rule: make a deliberate choice and be able to say why, which is the one thing a default never is.
The two domains
| code | UI | |
|---|---|---|
| Scanner | scripts/unslop_code_scan.py |
scripts/devibe_scan.py |
| Catalog | references/tells-code.md | references/tells-ui.md |
| Build method | references/fitting-the-codebase.md | references/choosing-a-look.md |
| What only this domain has | It executes. Compile and resolve imports before reading anything | Layout coherence, spacing, and overflow are invisible to the scanner |
What ships with it
6 files 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 · +5 lines 9e2d251d58a8
- 2mo ago First seen · 156 lines · 215 tokens per session scan A 0da49409ac4f
unslop is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed 1mo ago), licensed MIT. It adds 215 tokens to every session and 2,279 once invoked, about $0.0009 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.
unslop compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unsloplarsboes/Axon | Skill | 1 | 1mo ago | MIT | A | 215 | Claude Code |
| security-auditCoWork-OS/CoWork-OS | Skill | 537 | today | MIT | A | 38 | Claude Code, Codex |
| security-diff-scanCoWork-OS/CoWork-OS | Skill | 537 | today | MIT | A | 36 | Codex |
| github-reviewholon-run/holon | Skill | 194 | today | Apache-2.0 | A | 27 | Claude Code, Codex |
| code-reviewholon-run/holon | Skill | 194 | today | Apache-2.0 | A | 23 | Claude Code, Codex |
| github-pr-fixholon-run/holon | Skill | 194 | today | Apache-2.0 | A | 25 | Claude Code, Codex |
| code-health-auditholon-run/holon | Skill | 194 | today | Apache-2.0 | A | 39 | Claude Code, Codex |