Configuration reference

Cursor, Claude Code and Codex read project instructions from different files: Cursor from .cursor/rules/*.mdc, AGENTS.md and CLAUDE.md, Claude Code from CLAUDE.md (and AGENTS.md when no CLAUDE.md exists, from v2.1.277 on both release channels), Codex from an AGENTS.md chain plus config.toml. Loading order, scoping and size limits differ, and none of the tools warns when a rule fails to load (checked on Claude Code 2.1.283, Codex CLI 0.157.1 and @cursor/sdk 1.0.32).

This reference is for the developer or tech lead who owns a repository’s agent configuration. The typical failure is quiet: a rule scoped to API routes fires on every file, a personal CLAUDE.local.md stops Claude Code from reading the team’s AGENTS.md, or Codex drops the package instructions you wrote last week because the chain crossed its byte budget. Nothing errors. The agent just stops following the rule.

The entries below that name Claude Code 2.1.296, Codex 0.162.1 or a Cursor page were checked on 2026-10-12.

What this configuration reference gives you

• One table of which file each tool loads, from where, and when.
• Minimal, correct templates for .cursor/rules/*.mdc, CLAUDE.md, .claude/settings.json, AGENTS.md and config.toml.
• A one-source-of-truth layout for teams that use more than one tool.
• Commands that prove which instructions actually loaded, plus a CI budget check you can paste into a workflow.
• The silent failures, each with its recovery step.

For what to put in these files and what to cut, see Pruning CLAUDE.md and AGENTS.md. This page covers where the files go and how each tool loads them.

Which file does each AI coding tool read?

	Cursor†	Claude Code	Codex
Instruction file	.cursor/rules/**/*.mdc; also AGENTS.md in the project root and subdirectories, and CLAUDE.md (Cursor’s docs, 2026-10-12)	CLAUDE.md or .claude/CLAUDE.md; AGENTS.md when no CLAUDE.md exists	AGENTS.md in each directory from the project root to the working directory
Scoped rules	globs in .mdc frontmatter	.claude/rules/*.md with paths frontmatter	By directory only: a nested AGENTS.md
Personal, uncommitted	Not a repository file	CLAUDE.local.md (add it to .gitignore)	AGENTS.override.md (add it to .gitignore)
User-level	Cursor settings	~/.claude/CLAUDE.md, ~/.claude/rules/	~/.codex/AGENTS.md
Settings and permissions	Cursor settings; permissions.json in ~/.cursor/ and in the project’s .cursor/ (merged), sandbox.json for the sandbox, and from Cursor 3.24 the managed policy AgentRemoteWorkspaceAuthorities, which lets admins restrict Agent to approved remote workspaces (Cursor’s docs and release notes, 2026-10-12)	.claude/settings.json, .claude/settings.local.json	~/.codex/config.toml, .codex/config.toml in a trusted project
MCP servers	.cursor/mcp.json, ~/.cursor/mcp.json	.mcp.json (project scope)	[mcp_servers.<name>] in config.toml
Older formats still read	.cursorrules: legacy, and Cursor’s help says it “will be deprecated”; the @cursor/sdk 1.0.32 loader applies it as an always-on rule	.claude/commands/*.md (still works; now part of skills)	[profiles.<name>] tables (still parsed)
Check what loaded	Ask the agent (see the prompt below)	/context, /doctor prompt-audit	codex debug prompt-input

† The Cursor column follows the rule loader in Cursor’s agent SDK, @cursor/sdk 1.0.32, and Cursor’s documentation (checked 2026-10-12); see the note below.

How the Cursor rows were checked

cursor.com could not be reached when this page was first revised on 2026-09-26, so the Cursor behaviour on this page was read from the rule loader in Cursor’s own @cursor/sdk 1.0.32 package, which watches .cursor/rules/**/*.mdc, AGENTS.md, CLAUDE.md, CLAUDE.local.md, .cursorrules and .cursorignore. It loads CLAUDE.md only when third-party configuration is enabled. That package is Cursor’s agent SDK runtime, not the editor, so for the editor this page follows Cursor’s documentation, checked 2026-10-12. Project rules live in .cursor/rules as .mdc files, and “a plain .md file in .cursor/rules is ignored by the rules system”. Cursor supports AGENTS.md in the project root and in subdirectories, combines nested files with their parent directories (the more specific instructions take precedence), and reads CLAUDE.md the same way, always applied whatever alwaysApply says. Cursor’s help calls .cursorrules legacy, and “rules only apply to Agent (Chat)”: they do not apply to Tab completion, Inline Edit or Bugbot pull-request reviews. Re-check the rules page in Cursor’s documentation before you rely on a detail in production.

Cursor: rules in .cursor/rules/

Each rule is one .mdc file: YAML frontmatter, then Markdown. Three frontmatter fields decide when the rule enters the context.

---
description: "API route conventions for the Next.js App Router"
globs: src/app/api/**/*.ts
alwaysApply: false
---

- Validate every request body with the zod schema in `src/lib/schemas/`.
- Call the service layer; never query the database from a route.
- Return `{ ok: true, data }` or `{ ok: false, error }` with a matching status code.
- Run `npm run test -- src/app/api` before reporting the task complete.

The fields are checked in a fixed order, and the first matching row wins:

Frontmatter	Rule type	When it loads
alwaysApply: true	Always	Every request, whatever globs says
globs set	File-scoped	When the agent works with a matching file
Only description	Agent-selected	When the agent judges the description relevant
None of the three	Manual	Only when you attach the rule yourself

globs takes a comma-separated string (src/**/*.ts, src/**/*.tsx); a YAML list also works. Keep one topic per file and name files after the topic (api-routes.mdc, testing.mdc), so a reviewer can see from the file list what is always on. For setup inside the editor, see Cursor project rules.

Claude Code: CLAUDE.md, rules and settings

Where Claude Code looks for CLAUDE.md

Location	Scope	When it loads
Managed policy file (/etc/claude-code/CLAUDE.md on Linux, /Library/Application Support/ClaudeCode/CLAUDE.md on macOS)	Every user on the machine; cannot be excluded	At launch
~/.claude/CLAUDE.md, ~/.claude/rules/	You, in every project	At launch
./CLAUDE.md or ./.claude/CLAUDE.md, and each one in a parent directory	The team, through version control	At launch, root first
./CLAUDE.local.md	You, in this project	At launch
src/billing/CLAUDE.md (below the working directory)	That part of the tree	When Claude reads a file there
.claude/rules/*.md without paths	The project	At launch
.claude/rules/*.md with paths	Matching files	When Claude reads a matching file

Files are concatenated, not overridden, so a contradiction between two of them is resolved arbitrarily. Anthropic’s memory documentation recommends keeping each CLAUDE.md under 200 lines. A path-scoped rule looks like this:

---
paths:
  - "src/api/**/*.ts"
---

- Validate input with the zod schemas in `src/api/schemas/`.
- Errors use the `ApiError` class; never return a raw stack trace.

A lean project CLAUDE.md holds what the agent cannot read from the code: commands, boundaries and pitfalls.

CLAUDE.md

@AGENTS.md

## Claude Code only
- Use plan mode for any change under `src/billing/`.
- Before reporting done: `npm run typecheck && npm run lint && npm test`.

@path imports keep a long file organised, but they do not save context: imported files load at launch with the file that imports them. Block-level HTML comments (<!-- note -->) are stripped before injection, so maintainer notes cost no tokens.

How CLAUDE.md and AGENTS.md interact

From v2.1.277, Claude Code reads AGENTS.md when there is no CLAUDE.md, .claude/CLAUDE.md or CLAUDE.local.md in the working directory or above it. v2.1.281 extended this to Amazon Bedrock, Google Cloud, Foundry, LLM gateways and telemetry-off sessions. Builds older than v2.1.277 read CLAUDE.md only; both release channels are past that since stable reached 2.1.287 (checked 2026-10-12). Claude Code does not read AGENTS.local.md, AGENTS.override.md or anything under a .agents/ directory (Claude Code 2.1.296 memory docs, 2026-10-12), so Codex’s personal AGENTS.override.md never reaches it. The Project instructions setting in /config changes the default:

Value	What Claude reads
claude-md-or-agents-md (default)	CLAUDE.md files, or AGENTS.md when there is no CLAUDE.md
claude-md-and-agents-md	Both, each directory’s CLAUDE.md first; a file already imported is not read twice
claude-md	CLAUDE.md files only
managed-only	Only the managed CLAUDE.md and auto memory at launch

The @AGENTS.md import in the template above works on every channel and never loads the file twice, which makes it the safe choice for a team on mixed versions.

.claude/settings.json: permissions, not context

Settings control what Claude may do; they add no instructions. Precedence, highest first: managed settings, command-line arguments, .claude/settings.local.json, .claude/settings.json, ~/.claude/settings.json. List keys such as permissions.allow merge across files instead of replacing each other.

{
  "$schema": "https://json.schemastore.org/claude-code-settings.json",
  "permissions": {
    "allow": ["Bash(npm run lint)", "Bash(npm run test *)", "Bash(npx tsc --noEmit)"],
    "deny": ["Bash(git push *)", "Read(./.env)", "Read(./.env.*)"]
  }
}

Two rules catch teams out. allow rules from a committed file apply only after each teammate trusts the folder. And auto or bypassPermissions as permissions.defaultMode is ignored in project and local settings; it takes effect only from user settings, a --settings file or managed settings. Skills go in .claude/skills/<name>/SKILL.md; existing .claude/commands/*.md files keep working. For the full walkthrough, see Claude Code configuration and the Claude Code memory system.

These settings, hook fields and environment variables arrived or changed behaviour in Claude Code 2.1.284 to 2.1.296. Each row names the version, and everything from v2.1.293 on is on the latest channel only (stable is 2.1.292 on 2026-10-17; checked against Claude Code’s settings, hooks and environment-variable docs and its changelog).

Name	Where it goes	What it does	Version
allowedProviders	Managed settings	Limits which API providers a machine may use: "anthropic", "bedrock", "vertex", "foundry", "anthropicAws", "mantle", "customEndpoint" or "gateway". A session on an unlisted provider is refused at startup, at login and when it next contacts the API. "customEndpoint" is admitted only for the exact value that a managed env block pins. Unset means any provider	v2.1.285
onFailure	A command or http hook handler	"continue" (the default) or "block". With "block", a hook that can’t start, times out or exits with an unexpected code blocks the action instead of letting it through	v2.1.295 (latest)
CLAUDE_CODE_DISABLE_WEB_FETCH	Environment	1 turns off the WebFetch tool; WebSearch stays available	v2.1.285
CLAUDE_CODE_WEB_SEARCH_REFILLS_PER_HOUR	Environment	Rate at which a session’s WebSearch limit refills, in calls per hour: 100 by default in an interactive session, 0 (no refill) in a non-interactive one	v2.1.290
CLAUDE_CODE_DISABLE_1M_CONTEXT	Environment	1 turns off 1M-context support and holds models that default to a 1M window to 200K. Since v2.1.287, Opus 4.7+ and Fable default to 1M on Bedrock, Google Cloud, Foundry and the Claude apps gateway, with no [1m] suffix	the variable is older; its effect changed in v2.1.287
CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL	Environment	Runs every workflow agent on one model while other subagents keep theirs	v2.1.296 (latest)
MCP_PROTOCOL_NEGOTIATION	Environment	legacy stops Claude Code from probing servers for MCP protocol revision 2026-07-28; local (stdio) servers negotiate it by default on every install from v2.1.292	the variable needs v2.1.221; the stdio default changed in v2.1.292
CLAUDE_CODE_NONSTREAMING_TIMEOUT_RETRIES	Environment	Limits how often Claude Code re-sends a non-streaming request that times out; 0 fails on the first timeout	v2.1.285
CLAUDE_CODE_OVERLOADED_RETRY_BASE_DELAY_MS	Environment	Starting delay of the backoff between retries of a request the API rejects as overloaded (529), in place of the default 500; whole milliseconds from 500 to 32000	v2.1.292
CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS	Environment	With CLAUDE_CODE_RETRY_WATCHDOG set, the longest time each API request spends waiting out 429 and 529 errors; unset means no limit	v2.1.295 (latest)

Codex: AGENTS.md and config.toml

How Codex builds the AGENTS.md chain

Codex walks up from the working directory to the project root (the nearest directory containing .git, unless project_root_markers says otherwise). It then reads one file per directory, root first, and concatenates them. In each directory it takes the first file that exists from this list:

1. AGENTS.override.md: a personal replacement for that directory’s AGENTS.md. Parent directories still load.
2. AGENTS.md.
3. Each name in project_doc_fallback_filenames, in order.

Files below the working directory are not read, so start Codex in the package you are changing (codex --cd packages/api). The global ~/.codex/AGENTS.md arrives as user instructions and does not count against the project budget. A project marked untrusted supplies no AGENTS.md at all (since Codex CLI 0.150.0).

What goes in config.toml

Codex merges config.toml layers in this order, later winning: /etc/codex/config.toml, ~/.codex/config.toml, a profile selected with --profile <name> (~/.codex/<name>.config.toml), .codex/config.toml files from the project tree, then -c key=value flags. Project layers apply only in a trusted project, so a committed .codex/config.toml is a real team setting once each developer trusts the repository. Administrators enforce limits in requirements.toml, which users cannot override.

# .codex/config.toml (committed) or ~/.codex/config.toml (personal)

# Leave `model` unset to follow Codex's bundled default; pin a model only when your evals say so.

approval_policy = "on-request"   # untrusted | on-request (default) | granular | never

# Permission profiles are beta (Codex CLI 0.138.0 and later).
# Built-ins: ":read-only", ":workspace", ":danger-full-access". Do not combine with sandbox_mode.
default_permissions = ":workspace"

project_doc_max_bytes = 32768                    # default: 32 KiB across all project AGENTS.md files
project_doc_fallback_filenames = ["CLAUDE.md"]   # read CLAUDE.md where a directory has no AGENTS.md

[mcp_servers.playwright]
command = "npx"
args = ["@playwright/mcp@latest"]

On the command line, -a accepts only on-request and never in Codex CLI 0.157.1 through 0.162.1 (checked 2026-10-12); untrusted and granular are config.toml values. Put the flag before a subcommand: codex -a never exec "…". Current model names and defaults live on the models hub. For the full option set, see Codex configuration and writing AGENTS.md for Codex.

Codex 0.158.0 to 0.162.1 added or changed these keys and features (checked against the 0.162.1 config schema, its feature list and the release notes on 2026-10-12):

Key or feature	File	What it does	Version
daybreak	config.toml	Default Daybreak preference for new threads and non-interactive turns. daybreak = true alone is not enough: Daybreak is opt-in through features.cli_daybreak = true or --enable cli_daybreak, and /daybreak is unavailable until then	0.161.0
features.cli_daybreak	config.toml	The gate for Daybreak: under development, off by default	0.161.0
audio.microphone_channel	config.toml	One-based microphone channels to mix for voice input; unset mixes all input channels	between 0.157.1 and 0.162.1
auto_review.circuit_break_action	config.toml	Whether circuit-breaker interruptions include a structured error; strict mode writes errors that older clients may not recognise when reading shared history. Defaults to default	between 0.157.1 and 0.162.1
auto_review.conversation_history_max_output_tokens	config.toml	Maximum estimated tokens per history-tool response in automatic review; defaults to 4,000	between 0.157.1 and 0.162.1
auto_review.experimental_conversation_history_prompt	config.toml	Experimental replacement for the history-retrieval instructions when history tools and Apps are enabled; blank uses the built-in prompt	between 0.157.1 and 0.162.1
tui.mouse_scroll_speed	config.toml	Mouse-wheel speed multiplier for transcript scrolling; defaults to 1.0	0.162.0
allow_mxc	requirements.toml	Admin requirement for the Windows MXC sandbox	0.161.0
features.write_stdin_approval	config.toml	Terminal-input approval for commands running with elevated permissions; stable and on by default	0.158.0
features.api_key_model_discovery	config.toml	Model discovery when you sign in with an API key; stable and on by default	0.161.0
features.ultrafast_mode	config.toml	The Ultrafast speed tier for GPT-6 Astra and GPT-6.1 Sol; stable and on, but in Codex it needs an eligible plan (see the pricing analysis)	between 0.157.1 and 0.162.1
tui.prompt_suggestions	config.toml	Removed together with the automatic follow-up prompt suggestions; delete it	removed in 0.159.0

Codex 0.162.0 also preserves CRLF line endings in apply_patch without an opt-in, so the apply_patch_preserve_line_endings feature no longer exists.

How do you share one instruction set across all three tools?

Make AGENTS.md the source of truth: Codex reads it natively, Claude Code reads or imports it, and Cursor reads it in the project root and in subdirectories (Cursor’s docs, checked 2026-10-12). Cursor needs no copy of it in .cursor/rules/; keep that folder for rules that only Cursor needs. Then add only what each tool needs on top.

AGENTS.md                      # shared: stack, commands, boundaries, done criteria
packages/api/AGENTS.md         # package rules; Codex and Cursor read it directly
CLAUDE.md                      # "@AGENTS.md" plus Claude-only notes (Cursor reads it too)
.claude/rules/api.md           # paths: packages/api/** (Claude's copy of scoped rules)
.cursor/rules/test-files.mdc   # globs: **/*.test.ts (Cursor-only scoping a directory cannot express)
.codex/config.toml             # project_doc_max_bytes, approval policy, MCP servers

Cursor

No copy of the shared layer is needed: Cursor reads AGENTS.md in the project root and in subdirectories, combines nested files with their parents (the more specific instructions take precedence), and reads CLAUDE.md the same way, always applied (Cursor’s rules docs and help, checked 2026-10-12). Add a .mdc rule only for what is specific to Cursor, such as file-type scoping that a directory cannot express, like **/*.test.ts, with globs. Because Cursor applies CLAUDE.md too, write its Claude-only notes so they do no harm in Cursor.

Claude Code

Put @AGENTS.md on the first line of CLAUDE.md. With a root CLAUDE.md present, the default setting skips every AGENTS.md that is not imported, including packages/api/AGENTS.md. Either set Project instructions to claude-md-and-agents-md (from v2.1.277), or mirror package rules in .claude/rules/ with paths.

Codex

No change: AGENTS.md is Codex’s native file. If the repository already has CLAUDE.md files and no AGENTS.md, set project_doc_fallback_filenames = ["CLAUDE.md"] instead of duplicating them.

When the duplicated scoped rules start to drift, a sync tool can generate them from one source; see rules sync tools.

Copy-paste prompt: consolidate instruction files into AGENTS.md

Inventory every agent instruction file in this repository: AGENTS.md, AGENTS.override.md,
CLAUDE.md, CLAUDE.local.md, .claude/CLAUDE.md, .claude/rules/**, .cursor/rules/**, .cursorrules.
For each, list its path, size in bytes, and which tools load it.
Then propose a consolidation:
1. Move instructions every tool needs into the root AGENTS.md or the package AGENTS.md
   nearest to the code they govern.
2. Reduce CLAUDE.md to "@AGENTS.md" plus Claude-only notes.
3. Cursor reads AGENTS.md and CLAUDE.md directly, so do not copy the shared layer into
   .cursor/rules. Keep .cursor/rules/*.mdc only for rules specific to Cursor, and
   .claude/rules/*.md for Claude Code's path scoping.
4. Flag contradictions between files and instructions the code already makes obvious.
Show the proposed file tree and a diff. Do not write any files until I approve.

How do you prove which instructions loaded?

Reading every instruction file after each change does not scale. Check what the agent actually received, gate the size in CI, and give the files an owner.

1. Add a canary line. Put a short, unique sentence in each file, such as Instruction set: api-rules-2026-09. It costs a few tokens and makes loading visible.

2. Inspect the loaded context.

   Cursor

   Open a file the rule should cover, then run the prompt at the end of these steps. Every file-scoped rule you expect must appear by its canary.

   Claude Code

   Run /context and check that each expected file appears under Memory files. From v2.1.283 (both release channels on 2026-10-12), run /doctor prompt-audit to find stale, contradictory or broken instructions. It proposes edits and changes nothing until you approve.

   Codex

   Render the exact model-visible input from the directory you work in, then search it for the canary:

   cd packages/api
   codex debug prompt-input | grep -c "Instruction set: api-rules-2026-09"

   0 means the file was skipped: the project is marked untrusted, the file sits below the working directory, or the budget ran out before it.

3. Gate the Codex budget in CI. The script fails when any root-to-leaf chain exceeds 32 KiB. Run it from the repository root. It counts AGENTS.override.md and AGENTS.md only; if you set project_doc_fallback_filenames, add those names to names, or a repository that relies on CLAUDE.md passes with nothing measured.

   #!/usr/bin/env bash
   # Fails when any root-to-leaf instruction chain exceeds Codex's default 32 KiB budget.
   set -euo pipefail
   limit=32768
   # Names Codex looks for in each directory, in order. If you set
   # project_doc_fallback_filenames, append those names too, e.g. CLAUDE.md.
   names=(AGENTS.override.md AGENTS.md)
   match=(-false)
   for name in "${names[@]}"; do match+=(-o -name "$name"); done
   status=0
   while IFS= read -r leaf; do
     dir=$leaf
     total=0
     while :; do
       for name in "${names[@]}"; do
         if [ -f "$dir/$name" ]; then
           total=$((total + $(wc -c < "$dir/$name")))
           break
         fi
       done
       [ "$dir" = "." ] && break
       dir=$(dirname "$dir")
     done
     if [ "$total" -gt "$limit" ]; then
       echo "over budget: $total bytes in the chain ending at $leaf/"
       status=1
     fi
   done < <(find . \( "${match[@]}" \) -not -path '*/node_modules/*' -exec dirname {} \; | sort -u)
   exit "$status"

4. Assign an owner. Instruction files change agent behaviour on every run, so review them like code. The tech lead, or whoever owns the build, approves changes through CODEOWNERS:

   AGENTS.md                @your-org/eng-leads
   **/AGENTS.md             @your-org/eng-leads
   CLAUDE.md                @your-org/eng-leads
   .claude/                 @your-org/eng-leads
   .cursor/rules/           @your-org/eng-leads
   .codex/                  @your-org/eng-leads

Replace @your-org/eng-leads with your own team handle. Organisation-wide policy that individuals must not override belongs in managed settings rather than in the repository; see managed agent policy.

Copy-paste prompt: report the instructions you received

Before doing anything else, list every project instruction file and rule you have loaded
in this session: the path, and the line that starts with "Instruction set:" if the file has one.
Then list any instruction file in this repository that exists but that you did not load,
and say why (scope, glob, directory, size limit, or setting). Do not read new files to
answer the first list; report only what is already in your context.

When configuration files fail silently

Symptom	Cause	Recovery
A Cursor rule scoped to API routes applies to every file	alwaysApply: true overrides globs	Set alwaysApply: false; keep globs
A Cursor rule never loads	The file ends in .md, not .mdc, or sits outside .cursor/rules/	Rename to .mdc under .cursor/rules/
Claude Code stopped following the team’s AGENTS.md	Someone added CLAUDE.local.md or a CLAUDE.md, which switches the fallback off	Put @AGENTS.md at the top of CLAUDE.md, or set Project instructions to claude-md-and-agents-md
Claude Code ignores AGENTS.md on one laptop	That install is older than v2.1.277 or disabled the built-in agents-md plugin	Use the @AGENTS.md import; it works on every version
Claude Code forgets an instruction after /compact	The instruction was given only in chat, or it lives in a nested file or path-scoped rule that has not reloaded	Move it into the root CLAUDE.md; nested files reload when Claude reads a file there
Codex ignores the newest package rules	The chain exceeded project_doc_max_bytes; the crossing file was cut and later files skipped	Run the budget script, trim the root file, or raise project_doc_max_bytes
Codex ignores packages/api/AGENTS.md	Codex was started at the root; files below the working directory are not read	Start Codex with --cd packages/api
Codex ignores the committed .codex/config.toml or all project AGENTS.md files	The project is not trusted, or is marked untrusted	Trust the project when Codex asks, then re-run codex debug prompt-input
codex -a untrusted fails with “invalid value”	In 0.157.1 through 0.162.1, -a accepts only on-request and never	Set approval_policy = "untrusted" in config.toml
Codex’s AGENTS.override.md has no effect in Claude Code	Claude Code does not read AGENTS.local.md, AGENTS.override.md or anything under .agents/	Put the content in AGENTS.md, or import the file from CLAUDE.md with @path
defaultMode: "auto" in .claude/settings.json has no effect	Project and local settings cannot set auto or bypassPermissions	Set auto in user or managed settings; never set bypassPermissions outside a disposable, network-restricted sandbox

Where to go next with agent configuration

• Pruning CLAUDE.md and AGENTS.md: decide which lines belong in which file, and measure what removing them changes.
• Command reference: the CLI flags and slash commands used on this page.
• Installing and managing skills: when a workflow belongs in a skill rather than an instruction file.
• Glossary: the terms used across these three tools.