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 iCodeCraft/anti-slop --skill kill-slopgit clone --depth 1 https://github.com/iCodeCraft/anti-slopWrote 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/icodecraft/anti-slop/kill-slop)<a href="https://agentmods.dev/skills/icodecraft/anti-slop/kill-slop"><img src="https://agentmods.dev/badge/skills/icodecraft/anti-slop/kill-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.
<a href="https://agentmods.dev/skills/icodecraft/anti-slop/kill-slop"><img src="https://agentmods.dev/badge/skills/icodecraft/anti-slop/kill-slop.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 | $0.00096 | $0.01429 |
| Opus 5 | $0.00048 | $0.00714 |
| Sonnet 5 | $0.00019 | $0.00286 |
| Haiku 4.5 | $0.00010 | $0.00143 |
Grade A, and why
kill-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 10d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kill Slop
Force a minimal, merge-ready diff. Prefer the smallest change that fully solves the stated task.
Hard rules
- NEVER create a file unless the task clearly needs it or a navigability split below applies
- NEVER add a dependency unless the user asked or existing code already requires it
- NEVER refactor unrelated code "while you're here"
- NEVER add comments that restate what the code already says
- NEVER introduce abstractions (wrappers, helpers, factories, "utils") for a single use
- NEVER expand scope beyond the user's request
- NEVER invent TODOs, stubs, or "for later" scaffolding
- NEVER search, list, or read outside the workspace root unless the user explicitly asks
- NEVER browse sibling projects, home, Desktop, or prior chats for “patterns” or inspiration
- NEVER invent Clean Architecture / SOLID folder trees (
domain/,application/,infrastructure/,usecases/, …) unless the repo already uses that layout - MUST match existing project patterns before inventing new ones
- MUST prefer editing an existing file over adding a new one
- MUST delete dead code you introduce; do not leave unused imports/vars
User intent wins
Default to minimal. If the user explicitly asks for more structure, obey that request.
Examples of explicit asks (do what they asked):
- "use Clean Architecture / hexagonal / feature folders"
- "scaffold the full project layout"
- "add dependency X" / "set up Prisma / NextAuth / …"
- "extract a shared abstraction" / "add a utils module"
- "write tests" / "add comments explaining this"
Do not override an explicit ask in the name of kill-slop. Minimalism applies when they did not request the heavier shape. If the ask is ambiguous, prefer minimal and say what you skipped.
File shape (navigability)
Goal: easy to walk for humans and agents — without architecture theater.
Default: colocate. Edit the file/folder that already owns this concern.
Split only when ALL of these hold:
- Pain now — the file is already hard to navigate (rough guide: ≳300–400 lines, or clearly mixed unrelated concerns), and your change would make it worse
- One unit — you’re extracting a single cohesive piece (one component, one route handler, one pure helper) with a clear name
- Local fit — the new file follows an existing nearby pattern (same folder / naming). If there is no pattern, still colocate beside the caller — do not invent a new layer
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.
- 10d ago First seen · 125 lines · 96 tokens per session scan A dc43e1161496
kill-slop is a skill published in the GitHub repository iCodeCraft/anti-slop (27 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,429 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
greenfield
Parallel persona planning for new projects. Research agent runs first to build domain context, then Architect, PM, and Security agents run in parallel. Synthesis agent combines all perspectives into a detailed GSD-style PLAN.md with Tensions section.
brownfield-drift
Enforces architecture boundaries defined in PLAN.md. Use when a PR crosses module/service boundaries, when the dev asks "are we following the architecture?", or as a scheduled architecture health check. Not for querying what a module does — use brownfield-chat for that.
pr-review
Fix engine for PR review comments. Fetches review comments (Gemini bot or human), categorizes by impact, posts a prioritized fix queue, and applies fixes on dev approval. Called directly for quick fixes, or internally by pr-review-agent as part of full PR review.
wednesday-git
Unified Git workflow. Manages the entire task lifecycle: branch creation (sprint), atomic commits (git-os), and PR opening (pr-create).
standards-kit
Unified development and design standards. Enforces code quality (complexity < 8), strict naming conventions, and the mandatory use of approved UI component libraries.
codebase-intel
Unified codebase intelligence. Handles all questions about structure, logic, risk, and dependencies. Combines natural-language Q&A with deterministic lookups and pre-edit blast radius checks.