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 agentmods add instructions/scanaislop/aislop/agents-mdgit clone --depth 1 https://github.com/scanaislop/aislopWrote 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/instructions/scanaislop/aislop/agents-md)<a href="https://agentmods.dev/instructions/scanaislop/aislop/agents-md"><img src="https://agentmods.dev/badge/instructions/scanaislop/aislop/agents-md.svg" alt="Measured on agentmods" 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 | $0.01785 | $0.01785 |
| Opus 5 | $0.00892 | $0.00892 |
| Sonnet 5 | $0.00357 | $0.00357 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade C, and why
aislop AGENTS.md scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **No Unix-only shell in scripts.** `rm -rf`, `cp`, `mv`, etc. fail under How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Instructions for aislop
This file provides context for AI coding assistants (Claude Code, OpenCode, Copilot, Cursor, etc.) working on the aislop codebase.
What is aislop?
aislop is a unified code-quality CLI that catches the lazy patterns AI coding tools leave behind. It runs formatting, linting, code-quality, AI-pattern, architecture, and security checks behind a single command and returns a score out of 100.
- npm package:
aislop - CLI binary:
aislop - Config directory:
.aislop/ - Repository: https://github.com/scanaislop/aislop
Build & test commands
pnpm install # Install dependencies
pnpm build # Build with tsdown (tsdown cleans dist itself)
pnpm typecheck # tsc --noEmit
pnpm test # Build + vitest run
pnpm vitest run # Run tests without rebuilding (faster iteration)
pnpm scan # Build + run aislop on itself
node dist/cli.js scan . # Run after building manually
Cross-platform scripts
Contributors and CI run on Linux, macOS, and Windows. Keep package.json
scripts portable:
- No Unix-only shell in scripts.
rm -rf,cp,mv, etc. fail under cmd.exe on Windows. tsdown already cleans its output directory before each build, so an explicitrm -rf distis redundant; thebuildscript is justtsdown. - No
VAR=value cmdprefixes. cmd.exe cannot parse a leading env-var assignment, soNODE_ENV=production tsdownerrors with'NODE_ENV' is not recognized. If a script genuinely needs an env var set cross-platform, add thecross-envdev dependency and usecross-env VAR=value cmd. - A green Linux CI run is not a Windows guarantee. A handful of
path/permission tests (home-dir resolution,
0600permission bits, repo-relative path conversion) are environment-specific and may fail locally on Windows while passing in CI. Emit forward-slash paths in diagnostics so/-anchored classifiers match on every OS.
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.
- 4d ago First seen · 152 lines · 1,785 tokens per session scan C 12672d6dab63
aislop AGENTS.md is an instructions file published in the GitHub repository scanaislop/aislop (593 stars, last pushed 3d ago), licensed MIT. It adds 1,785 tokens to every session, about $0.0089 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
agent-skills AGENTS.md
Instructions for AsyrafHussin/agent-skills, covering agent skills repository, skills overview, usage and contributing.
agent-skills CLAUDE.md
Instructions for AsyrafHussin/agent-skills, a project described as: Skills for AI coding agents — Laravel, PHP, React, TypeScript, testing, security, and code quality.
brooks-lint AGENTS.md
AGENTS.md instructions for hyhmrright/brooks-lint, covering agents.md, core purpose, skill integration, engineering standards and project structure.
logic-lens GEMINI.md
Instructions for hyhmrright/logic-lens, covering logic-lens — developer guide (gemini cli), invoking skills, installation, project layout and key conventions.
sdlc-quality copilot-instructions.md
Instructions for zircote-plugins/sdlc-quality, covering copilot instructions for sdlc plugin, project overview, repository structure, key conventions and rfc 2119 terminology.
plan-forge dapr.instructions.md
Dapr patterns for .NET — building blocks, component config, sidecar architecture, multi-tenant isolation, workflows, state management, secrets.