no-slop

no-slop is a skill for Codex from jkomyno/.dotfiles. It costs 39 tokens per session (540 once invoked), scanned A, original, MIT.

A coding guide for removing code and writing that make claims without enough evidence. It focuses on keeping the original intent while making code and explanations more exact.

In plain words
What is it for?
Cleaning up code, comments, and prose that are imprecise or formulaic. It can also be used to install an Oxlint policy that checks for these issues.
Why use it?
It helps reduce unnecessary abstractions, vague wording, and unsupported assumptions. It also addresses weak TypeScript contracts, which describe data or behavior too loosely.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

Good fit Cleaning up code, comments, and prose that are imprecise or formulaic. It can also be used to install an Oxlint policy that checks for these issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jkomyno/.dotfiles/no-slop
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 jkomyno/.dotfiles --skill no-slop
Clone the repo
git clone --depth 1 https://github.com/jkomyno/.dotfiles

Made for: Codex.

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 no-slop

README.md
[![agentmods](https://agentmods.dev/badge/skills/jkomyno/.dotfiles/no-slop/github.svg)](https://agentmods.dev/skills/jkomyno/.dotfiles/no-slop)
Your own site
<a href="https://agentmods.dev/skills/jkomyno/.dotfiles/no-slop"><img src="https://agentmods.dev/badge/skills/jkomyno/.dotfiles/no-slop/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 no-slop

Your own site · 80×15
<a href="https://agentmods.dev/skills/jkomyno/.dotfiles/no-slop"><img src="https://agentmods.dev/badge/skills/jkomyno/.dotfiles/no-slop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 540 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 $0.00039 $0.00540
Opus 5 $0.00019 $0.00270
Sonnet 5 $0.00008 $0.00108
Haiku 4.5 $0.00004 $0.00054

Measured 12d ago against content hash e2ccd9f2ba0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

no-slop 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 12d ago.

The scan reads SKILL.md. This mod also ships 28 executable files (assets/anti-slop/effect/index.ts, assets/anti-slop/effect/rules/no-service-constructor-imports.ts, assets/anti-slop/index.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

target/home/.agents/skills/no-slop/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

No slop

Treat slop as work that claims more than it proves. Remove it without flattening the author's intent or rewriting sound code for taste.

Principles

  • Preserve evidence. Keep known values, keys, invariants, and source facts visible.
  • State the exact thing. Prefer domain names and direct claims over generic containers or abstract labels.
  • Contain uncertainty. Parse and normalize external input once per ownership boundary. Resolve process configuration at the composition root.
  • Prefer direct mechanics. Make data flow, control flow, and ownership easy to follow.
  • Make every layer earn its place. An abstraction, guard, test, comment, or sentence must add information or enforce a contract.
  • Keep deliberate voice. Remove formulas and filler, then check that the result still sounds authored.

Work

  1. Read the full target and its local conventions.
  2. Identify the claims the code or prose makes.
  3. Collect low-evidence candidates before changing them.
  4. Check each candidate against context. Keep intentional choices that carry meaning.
  5. Make the smallest coherent edit that improves precision.
  6. Verify the changed contract at its real boundary.
  7. Report the result, the evidence, and any remaining uncertainty.

TypeScript

Read TypeScript before writing or reviewing TypeScript or JavaScript. When the task evaluates, configures, fixes, or installs no-slop Oxlint rules, also read Oxlint policy. Apply repository rules first. Use these references as strict defaults, not permission for an unrelated rewrite.

Technical prose

  • Put the result, claim, or decision first.
  • Cut throat-clearing, verdict fragments, repeated summaries, unsupported praise, and vague intensifiers.
  • Do not pad a list or manufacture a contrast for rhythm.
  • Preserve facts, numbers, names, citations, structure, and deliberate phrasing during a wording-only pass.

Guardrails

  • Do not replace valid dynamic behavior or explicit uncertainty only to satisfy a heuristic.
  • Do not expand a local cleanup into a broad refactor.
  • Do not invent compatibility paths, fallbacks, recovery behavior, or defensive checks without evidence.
  • Do not add tests for unchanged behavior, trivial wiring, generated code, or implementation details.
  • Do not weaken types, lint rules, assertions, or tests to make a check pass.
  • Do not present a style preference as a correctness finding without evidence.

Read the full file on GitHub · 48 lines

Files

What ships with it

32 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.

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. 12d ago First seen · 48 lines · 39 tokens per session scan A e2ccd9f2ba0a

Subscribe to this mod's changes

no-slop is a skill published in the GitHub repository jkomyno/.dotfiles (5 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 540 once invoked, about $0.0002 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.