pz AGENTS.md

pz AGENTS.md is an instructions file for Codex, OpenCode from joelreymont/pz. It costs 1,183 tokens per session, scanned A, original, MIT.

A repository guide for agents building a Zig command-line tool with a text-based interface. It defines the project’s rules, including how to read files, report progress, manage changes, and coordinate parallel work.

In plain words
What is it for?
Use it when planning changes, inspecting code, running multi-agent work, or creating and syncing changes with Jujutsu.
Why use it?
It keeps agent work consistent and makes important decisions visible instead of relying on hidden assumptions or outdated compatibility code.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/joelreymont/pz/agents-md
Clone the repo
git clone --depth 1 https://github.com/joelreymont/pz

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for pz AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/joelreymont/pz/agents-md.svg)](https://agentmods.dev/instructions/joelreymont/pz/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/joelreymont/pz/agents-md"><img src="https://agentmods.dev/badge/instructions/joelreymont/pz/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,183 This file is loaded in full into every session.
When invoked 1,183 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01183 $0.01183
Opus 5 $0.00592 $0.00592
Sonnet 5 $0.00237 $0.00237
Haiku 4.5 $0.00118 $0.00118

Measured 5d ago against content hash 8bdc3f56536f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pz 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 5d 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.

AGENTS.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Rules

Mission

Build pz: a Zig CLI harness with TUI. Do not optimize for compatibility with pi.

Core Constraints

  • Correctness over speed.
  • Use hard cutovers only: no legacy support, compatibility shims, or fallback paths.
  • No silent fallbacks.
  • Root-cause fixes only.
  • Keep names short and clear.
  • Keep hot paths allocation-aware.

Read Window Rule

  • Use rg -n to find the anchor first.
  • Default file reads to a 20-line window around the anchor.
  • If that is insufficient, double the window: 40, then 80, then 160.
  • Only start wider when it is obvious up front that 20 lines cannot contain the relevant construct.

Trace Rule

  • Emit terse commentary traces during active work so the user can see progress.
  • Include a trace before substantial reads, edits, test runs, merges, and agent launches.
  • Keep traces factual and short.

Source Control

Use jj, not git.

  • New change: jj new
  • Describe change: jj describe -m "<imperative message>"
  • Sync: jj git fetch / jj git push

Parallel Work (Required)

For multi-agent work, use separate jj workspaces.

Default shape:

  1. Keep 1 local lane for integration, rebases, merges, flakes, and shared-surface debugging.

  2. Launch only 2-3 worker lanes by default.

  3. Expand past 3 workers only if the next dots are truly disjoint in files and dependencies.

  4. Create workspaces under .jj-ws/ (see jj skill for commands).

  5. Assign file ownership per workspace.

  6. Do not edit files owned by another workspace.

  7. Reconcile by rebasing/squashing after each track stabilizes.

File Ownership Rule

If a file is touched by another active agent, stop and reassign before editing. Do not launch overlapping dots in parallel just because they look “small”. If dots overlap in runtime/provider/session/core surfaces, serialize them unless a prior dot closes the dependency.

Commit Rule

Only include files changed by the current agent/task. No broad staging.

Agent Reporting Rule

Agents must report what they CHANGED (files, lines, insertions/deletions), not claim things were "already done." If no changes needed, explain why with file:line evidence. Never declare victory without a diff.

Read the full file on GitHub · 122 lines

Changes

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.

  1. 5d ago First seen · 122 lines · 1,183 tokens per session scan A 8bdc3f56536f

Subscribe to this mod's changes

pz AGENTS.md is an instructions file published in the GitHub repository joelreymont/pz (95 stars, last pushed 5mo ago), licensed MIT. It adds 1,183 tokens to every session, about $0.0059 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens