Install
$ agentstack add skill-icodecraft-anti-slop-kill-slop ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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
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
If only (2) is true (“I could extract this”), do not split.
When you split:
- MUST put the new file next to related code (same directory)
- MUST fix imports; no dead re-exports “for convenience”
- MUST keep the diff on this task — no repo-wide re-org
- NEVER split for SOLID, cleanliness, or “future features”
- NEVER create
utils//helpers//common//lib/for a single function unless that folder is already the repo convention - If unsure: don’t split — say so in the summary
Greenfield: prefer flat under one root (src/ is enough) until real navigability pain appears.
Diff budget
Before writing code, decide:
- Goal — one sentence: what changes for the user
- Touch list — the fewest files that can achieve it
- Non-goals — what you will not do
If the touch list grows past ~5 files for a small task, stop and shrink the plan.
If the workspace is empty or has no prior pattern, implement the smallest reasonable solution in-repo. Do not leave the workspace to find examples.
Style
- Prefer boring, readable code over cleverness
- Handle real error paths the task needs; skip speculative ones
- Names should explain intent; if you need a comment, rename instead
- Tests: only when the repo already tests this area, or the user asks
Self-check (before finishing)
Answer these. If any fails, fix before ending:
- [ ] Every changed line serves the stated goal
- [ ] No new files that could be inlined into an existing one
- [ ] Any new file exists only for navigability (or explicit need) — not architecture cosplay
- [ ] New files sit beside related code and match repo layout
- [ ] No new deps
- [ ] No drive-by renames/moves/refactors
- [ ] No obvious comments (
// import x,// return result) - [ ] No out-of-workspace reads or “inspiration” fishing
- [ ] Diff is something a senior would merge without asking "why is this here?"
Output
When summarizing, say what you changed and what you deliberately did not change. If you split a file, say why (navigability), in one sentence.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: iCodeCraft
- Source: iCodeCraft/anti-slop
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.