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 imisic/claude-marketplace --skill a-unslop-codegit clone --depth 1 https://github.com/imisic/claude-marketplaceWrote 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/imisic/claude-marketplace/a-unslop-code)<a href="https://agentmods.dev/skills/imisic/claude-marketplace/a-unslop-code"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-unslop-code/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/imisic/claude-marketplace/a-unslop-code"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-unslop-code.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 | $0.00187 | $0.01877 |
| Opus 5.5 | $0.00075 | $0.00751 |
| Sonnet 5.5 | $0.00037 | $0.00375 |
| Haiku 4.5 | $0.00019 | $0.00188 |
Grade A, and why
a-unslop-code 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 9d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
a-unslop-code
Part of the unslop family (see a-unslop-text, a-unslop-ui). Same shape: one global source, an auto-trigger, a Build mode and an Audit mode, a scanner that counts HIGH findings in its exit code, and an unslop-ignore line escape. This one is about code.
What it is not. It does not write good code and it has no house style. It removes the surface cues that read as machine-generated, and it points at the deeper tells that ship bugs, the ones no scanner catches. Whether the code is correct and right for the problem is still your call.
Sort every tell before you fix it
One question sets the order of work: is the code wrong, wrong for the job, or does it just look machine-made?
- Bug. A swallowed exception hides a failure you needed. A made-up API will not run. A
// rest of your codestub means the file is unfinished. Fix these because the code is broken, the same as any bug, whether or not anyone suspected AI. - Substance. Not a local bug, wrong for the job: tutorial-shaped boilerplate, an abstraction with one caller, a 2000-line change that should have been 50 because it ignored the repo. A compiler passes these; a reader comparing the diff to the neighbouring code does not.
- Cosmetic. The chat voice leaking into the file: emoji, a comment that restates the next line, a
process_datadoing eleven things, pasted "Good catch!" text. Worth removing, but nothing breaks if one survives.
The ranking behind this is blunt: the structural tells (tutorial shape, made-up APIs) lead by a wide margin, and the cosmetic ones people argue about sit far down. So the surface scan is the cheap part, not the job. A clean scan is not clean code.
How it fits your setup
If your project already has house rules for substance (smallest code that solves the problem, no abstraction for single-use code, surgical changes, comment the why not the what, no commented-out code, no v2/v3 files, remove orphaned imports), this skill does not restate them. It is the audit layer that catches a violation of them, plus the scanner for the cosmetic tells. If no-emoji and no-em-dash are already house rules for you, the scanner flags emoji in source on top of that.
What ships with it
12 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.
- agents/openai.yaml 103 B
- references/fitting-the-codebase.md 3.0 KB
- references/tells.md 12 KB
- scripts/unslop_code_scan.py 30 KB runs code
- tests/fixtures/clean/atomic_store.py 401 B runs code
- tests/fixtures/clean/cart.ts 365 B runs code
- tests/fixtures/clean/Invoice.php 269 B
- tests/fixtures/dirty/handler.py 361 B runs code
- tests/fixtures/dirty/integrity.diff 229 B
- tests/fixtures/dirty/notes/IMPLEMENTATION_SUMMARY.md 32 B
- tests/fixtures/dirty/surface.ts 89 B runs code
- tests/test_unslop_code_scan.py 37 KB runs code
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.
- 9d ago Changed · -55 lines d88b24ee9337
- 14d ago Changed d8cf3a32ec30
- 21d ago Changed f1b03653b527
- 1mo ago First seen · 128 lines · 187 tokens per session scan A cddce3b80fe1
a-unslop-code is a skill published in the GitHub repository imisic/claude-marketplace (1 stars, last pushed 9d ago), licensed MIT. It adds 187 tokens to every session and 1,877 once invoked, about $0.0007 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
recipe-schema-explore
Discover and introspect any Google Workspace API before using it — explore methods, parameters, and types.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
ring:using-assert
Using lib-observability/assert, Lerian's runtime assertion package, in two modes. Sweep Mode detects panic()/log.Fatal zero-panic violations, DIY invariant checks, hand-rolled domain predicates, and missing InitAssertionMetrics. Reference Mode catalogs the asserter lifecycle, domain predicates, observability trident…
api-design-reviewer
Use when reviewing API designs for consistency, usability, versioning, error semantics, security, backward compatibility, and developer experience before implementation or release.
review-rfc
Review an implemented RFC in a fresh context against its acceptance criteria, RULES.md and the test plan, and save the review to reviews/.