What is ez-stack AGENTS.md?

A set of project instructions for ez-stack, a command-line tool that manages stacked pull requests on GitHub. Stacked pull requests are related changes arranged so each one builds on the previous one.

It helps agents install or update ez-stack, configure its shell integration, create branches, and commit or manage pull-request stacks.

It prevents agents from using ordinary Git or GitHub commands when this repository requires the ez workflow.

ez-stack AGENTS.md — Instructions file by rohoswagger

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/rohoswagger/ez-stack/agents-md

Clone the repo

git clone --depth 1 https://github.com/rohoswagger/ez-stack

Made for: Codex, OpenCode.

Per session 1,103 This file is loaded in full into every session.

When invoked 1,103 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.

Model	Per session	Once invoked
Fable 5	$0.01103	$0.01103
Opus 5	$0.00551	$0.00551
Sonnet 5	$0.00221	$0.00221
Haiku 4.5	$0.00110	$0.00110

Measured 2d ago against content hash 5425188495c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ez-stack 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 2d 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 · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI agents working with ez-stack.

Purpose

ez is a CLI for managing stacked pull requests on GitHub. If a repository has .git/ez/stack.json, branch management and PR operations should go through ez, not raw git checkout -b, git commit, git push, or gh pr create.

Install or update the tool

# First install
pip install ez-stack
ez setup --yes    # configures shell integration (PATH + worktree auto-cd)

# Update to latest (auto-detects install method)
ez update

# Check for updates without installing
ez update --check

Requirements:

git
gh, authenticated via gh auth login
Rust/Cargo available to install ez-stack

Install the skill

Install the ez-workflow skill for the current user so all agents auto-discover it:

ez skill install
# Installs canonical skill to ~/.agents/skills/ez-workflow/SKILL.md
# Symlinks agent-specific skill roots like ~/.claude/skills/ and ~/.codex/skills/
# Works from any directory

This installs the workflow defined in SKILL.md.

Core rule

When .git/ez/stack.json exists, prefer these commands:

Create branch: ez create <name>
Commit specific files: ez commit -m "msg" -- path1 path2
Commit all tracked changes: ez commit -am "msg"
Commit tracked + untracked changes: ez commit -Am "msg"
Commit patch-selected hunks: git add -p then ez commit -m "msg"
Diff vs parent: ez diff --stat or ez diff --name-only
Get parent branch: ez parent
Push current branch and create/update PR: ez push
Push the stack: ez submit
Sync after trunk changes or merges: ez sync or ez sync --autostash
Repair a divergent GitHub native stack only when explicitly requested: ez sync --repair-native-stack
Adopt branches from GitHub PRs: ez adopt or ez adopt --pr 42
Inspect state programmatically: ez status --json and ez log --json

Avoid these raw commands in an ez-managed repo:

git checkout -b ... → ez create
git commit -m ... → ez commit -m
git push → ez push
gh pr create → ez push
git diff main...HEAD → ez diff

Read the full file on GitHub · 144 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.

2d ago First seen · 144 lines · 1,103 tokens per session scan A 5425188495c0

Subscribe to this mod's changes

ez-stack AGENTS.md is an instructions file published in the GitHub repository rohoswagger/ez-stack (23 stars, last pushed 20d ago), licensed MIT. It adds 1,103 tokens to every session, about $0.0055 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.

Git and workflow agents cli developer-tools stacked-prs

langgraph AGENTS.md

AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.

langchain-ai/langgraph · 477 tokens

agentgateway copilot-instructions.md

Copilot instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.

agentgateway/agentgateway · 41 tokens

ez-stack AGENTS.md