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/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/instructions/j3w1/j3w1zsh/agents-md"><img src="https://agentmods.dev/badge/instructions/j3w1/j3w1zsh/agents-md.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 | $0.02770 | $0.02770 |
| Opus 5.5 | $0.01108 | $0.01108 |
| Sonnet 5.5 | $0.00554 | $0.00554 |
| Haiku 4.5 | $0.00277 | $0.00277 |
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 27d 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 — 199 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.
- 27d ago Changed · -15 tokens per session 7a42eefa62ed
- 1mo ago Changed · +12 lines · +197 tokens per session 9542c649ecaf
- 1mo ago Changed · +63 lines · +1,084 tokens per session 31b9093ac54b
- 2mo 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 27d ago), licensed MIT. It adds 2,770 tokens to every session, about $0.0111 per session on Opus 5.5. 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.
j3w1zsh AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| j3w1zsh AGENTS.mdj3w1/j3w1zsh | Instructions file | 1 | 27d ago | MIT | A | 2,770 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |