stack AGENTS.md

A project instruction file for the stack command-line tool, a local utility for repairing dependent pull requests and merge requests after squash merging. It records the rules, commands, and safety requirements agents should follow.

In plain words
What is it for?
Guiding agents while they inspect, synchronise, merge, repair, and undo stacked changes in the stack project.
Why use it?
It keeps agents from using the tool in unsafe ways, such as changing protected branches or mutating repositories without explicit approval. It also defines backup, recovery, and undo expectations.

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/kitlangton/stack/agents-md
Clone the repo
git clone --depth 1 https://github.com/kitlangton/stack

Made for: Codex, OpenCode.

Per session 1,108 This file is loaded in full into every session.
When invoked 1,108 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 $0.01108 $0.01108
Opus 5 $0.00554 $0.00554
Sonnet 5 $0.00222 $0.00222
Haiku 4.5 $0.00111 $0.00111

Measured today against content hash f298af9f1c9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 today.

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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

stack agent notes

Intent

  • stack is a small, local-first CLI for stacked PR/MR repair in squash-merge repos.
  • Use the latest Effect v4 beta / effect-smol APIs throughout this project.
  • Normal editing and commits stay plain git.
  • Stack commands are only for stack inspection, intent, sync, merge, and undo workflows.

Safety rules

  • Bare stack sync must stay non-mutating, including scoped and keep-going runs.
  • Mutating commands need an explicit mode: --apply, or merge --auto for code-host auto-merge plus descendant repair.
  • Never mutate configured trunk branches like dev, main, or master.
  • Before rebasing a branch, create a local backup branch.
  • Before repair mutates Git or a hosted change, save an undo checkpoint. Merge child retargets use a pre-merge recovery journal; after the root lands, descendant repair starts from a post-merge baseline that never retargets children back onto the landed branch.
  • stack undo should restore the last applied mutation from the saved journal.

Current commands

  • status shows the relevant tracked stack, including open change titles when the code host is available.
  • skill prints the stack skill (full agent instruction set) for AI agent discovery from the installed package.
  • doctor checks Git, code-host access, stack metadata, trunks, and undo journal health without mutating anything.
  • track records parentage for an existing branch only when change target branches do not already encode the stack.
  • sync [branch] previews target-branch inference, stale metadata cleanup, and repairs without mutating branches, requests, or stack metadata using the tree summary output.
  • sync --apply [branch] applies the common maintenance workflow: remove stale local links, infer clear target-branch stack links, repair branches, retarget requests, refresh links, and show a concise tree summary. With a branch argument, sync only the stack containing that branch.
  • sync with no branch scopes to the current stack when the current branch is stack-relevant; when off-stack, it keeps the repo-wide behavior.
  • sync --apply --continue-on-failure / sync --apply --keep-going processes independent stacks, reports succeeded and failed stacks, preserves per-stack cleanup output, and exits nonzero if any stack failed.
  • sync should not auto-track standalone trunk-root requests; infer a trunk-root request only when another open request is based on it.
  • merge merges the oldest branch in a stack and immediately repairs descendants; when no branch is given, it infers the root from the current branch. It retargets immediate child requests before merge to preserve open work in auto-delete repos.
  • merge --auto retargets immediate child requests, enables code-host auto-merge, waits for merge, then repairs descendants.
  • merge --auto --through <branch-or-change> repeats root auto-merge and descendant repair until the target branch or request has landed.
  • history explains the most recent applied mutation from the undo journal.
  • undo restores the last applied mutation.

Read the full file on GitHub · 55 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. today First seen · 55 lines · 1,108 tokens per session scan A f298af9f1c9b

Subscribe to this mod's changes

stack AGENTS.md is an instructions file published in the GitHub repository kitlangton/stack (539 stars, last pushed 4d ago), licensed MIT. It adds 1,108 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 2026-08-31.

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

buildNext

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

next.js 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

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

spec-kit 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 · 7,040 tokens

langchain 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 · 4,345 tokens