Borrowing it
Nothing to install: this file belongs to j3w1/j3w1zsh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/j3w1/j3w1zsh/main/AGENTS.mdgit clone --depth 1 https://github.com/j3w1/j3w1zshWrote 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/j3w1/j3w1zsh/agents-md)<a href="https://agentmods.dev/instructions/j3w1/j3w1zsh/agents-md"><img src="https://agentmods.dev/badge/instructions/j3w1/j3w1zsh/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 5.1 | $0.01504 | $0.01504 |
| Opus 5 | $0.00752 | $0.00752 |
| Sonnet 5 | $0.00301 | $0.00301 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
j3w1zsh AGENTS.md 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 7d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
j3w1zsh agent instructions
Purpose and authority
j3w1zsh is a public, reproducible shell-first workstation framework for native official Arch
Linux, official Arch Linux under WSL 2, and native Termux on Android. Preserve its true-black,
blood-red, and warm-white design while keeping installation safe, resumable, explicit, and
portable across those three supported targets.
The current tracked code, schemas, presets, versions.env, wiki-lock.json, compatible pinned
Wiki pages, and tests are the source of truth. Conversation, generated state, screenshots, and
the former product are not current authority.
Use this precedence:
- explicit current owner authorization;
- this file and the authorized task scope;
- schemas, compatible pinned Wiki contract, and accepted repository policy;
- current code, Git, configuration, and runtime evidence;
- inference.
Stop rather than inventing a new business, security, schema, privilege, or release decision.
Start every run
- Read this file completely.
- Inspect
git status --short --branch, remotes, execution surface, and relevant worktrees. - Preserve unrelated human and agent work. Never assume a clean checkout, platform, or shell.
- Select the topic in
agent-context.json; load only its required code paths and compatible Wiki pages. Usej3w1zsh wiki context TOPICwhen the pinned Wiki is locally available. - Trace
bin/j3w1zshthrough the selectedscripts/commands/,scripts/lib/core/, platform adapter, and phase before changing user-facing behavior. - State scope, diagnose first, implement the smallest complete change, add focused regression coverage, update affected Wiki/root contract, and run the verification below.
If a decision exists only in conversation, encode the authorized decision in tracked code, tests, and the appropriate contract as part of the same change.
Security and privacy
- Never commit or print private keys, passwords, passphrases, tokens, OAuth/Codex sessions, GitHub CLI authentication, private repositories, documents, histories, caches, logs, installation IDs, personal absolute paths, or private database content.
- Public keys and Git identity still require an explicit documented reason before tracking.
- Keep privilege narrow, visible, planned, and platform-specific. Never add passwordless sudo.
- Never automate WSL unregister, home deletion, public SSH exposure, router/firewall changes, power-policy changes, secret migration, or arbitrary third-party execution.
- Validate every managed or recovery target under the intended home or named host adapter.
- Use authoritative downloads, immutable commits/releases where practical, and verified static
checksums. Never recommend piping mutable
maindirectly into a shell.
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.
- 7d ago First seen · 124 lines · 1,504 tokens per session scan A 5cf7be35e756
j3w1zsh AGENTS.md is an instructions file published in the GitHub repository j3w1/j3w1zsh (1 stars, last pushed yesterday), licensed MIT. It adds 1,504 tokens to every session, about $0.0075 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.