Comparison

A · AGENTS.md · yzhao062/anywhere-agents B · CLAUDE.md · yzhao062/anywhere-agents

What each file covers, counted
Dimension	Shared	Only in A	Only in B	Overlap
Sections	24	1	0	96%
Commands	37	2	2	90%
Section tags	7	0	0	100%

What each file covers

Sections

24 shared · 1 only in A · 0 only in B

− Codex MCP Integration
Bootstrap: Shared Config and Skills
Bootstrap block for project repos
Shared Agent Config (auto-fetched)
What gets shared
Override rules
Configuration Precedence
Session Start Check
Format
How to populate each field
User Profile
Agent Roles
Agent Fungibility
Memory and Persistence
Task Routing
Writing Defaults
Formatting Defaults
Git Safety
Mechanical Enforcement
Shell Command Style
Tool-Use Reliability
GitHub Actions Standards
Environment Notes
Local Skills Precedence
Cross-Tool Skill Sharing

Commands

37 shared · 2 only in A · 2 only in B

− npm install -g @openai/codex
− npm install -g @openai/codex@latest
+ git branch -d
+ git remote add/remove
pip install --user pyyaml
git clone
git commit
git push
git commit -m
git commit --amend
git push --force
gh pr create
git merge
git rebase
git reset --hard
git clean
git branch -d/-D
git checkout
git tag -d
git stash drop/clear
gh pr create/merge/close
gh repo delete
gh release create/delete/upload/edit
npm publish
npm unpublish
python -m twine upload
docker exec
python -c
git -C <path> <subcommand>
python <path>/script.py
git status
git diff
git log
git branch
git show
git stash list
git remote -v
git submodule status
git ls-files
git tag --list
git reset

Section tags

7 shared · 0 only in A · 0 only in B

setup
lint-format
code-style
git-pr
performance
do-not
agent-behaviour

Line diff

+18 added−35 removed306 unchanged89.7% identical

yzhao062/anywhere-agents · AGENTS.md

@@ −1 @@

1

3> **Claude Code / Codex / other agents -- determine your context before proceeding:**

@@ −178 @@

178- If the `superpowers` plugin is active, the router operates during the execution phase. Superpowers handles the outer workflow (brainstorm, plan, execute, verify); the router handles inner dispatch to the right domain skill.

179- If routing is ambiguous (multiple skills could apply), state the detected context and proposed skill, then ask the user to confirm.

180

181

182## Codex MCP Integration

183

184- Codex can run as an MCP server callable from Claude Code. Register at user scope (NOT project scope; project-scoped entries do not propagate across directories):

185 ```

186 claude mcp add codex -s user -- codex mcp-server -c approval_policy=never

187 ```

188 Writes to `~/.claude.json` `mcpServers`; session restart required for `/mcp` to pick it up. Available MCP tools after registration: `codex` (new prompt) and `codex-reply` (continue an existing session).

189- Prerequisites: Node.js + Codex CLI (`npm install -g @openai/codex`) + `OPENAI_API_KEY`.

190- **Recommended Codex defaults** (added to `~/.codex/config.toml` on POSIX or `%USERPROFILE%\.codex\config.toml` on Windows; the MCP server reads the same file as interactive sessions):

191 ```toml

192 model = "gpt-5.6-sol"

193 model_reasoning_effort = "max"

194 service_tier = "fast"

195

196 [features]

197 fast_mode = true

198

199 [desktop]

200 conversationDetailMode = "DEFAULT"

201 ```

202 **GPT-5.6 requires Codex CLI 0.144.0 or newer.** The GPT-5.6 family (`gpt-5.6-sol` flagship, `gpt-5.6-terra` mid, `gpt-5.6-luna` cheapest) is rejected by older builds with a hard `400`: `The 'gpt-5.6-sol' model requires a newer version of Codex.` Verified live: 0.142.5 and 0.143.0 fail, 0.144.0 and 0.144.1 work. If the model errors, run `npm install -g @openai/codex@latest` first. `gpt-5.6-sol` is Codex's own recommended default and suits the gatekeeper role; use `gpt-5.6-terra` for high-fan-out work (e.g. `prun` dispatch) where throughput beats peak capability.

203 **`service_tier` buys latency, never quality.** It selects the serving queue only: the model, its weights, and `model_reasoning_effort` are identical across tiers, so `standard` returns the same answer `fast` would, just generated more slowly. The three tiers are `flex` (lower-priority queue, roughly half rate, availability not guaranteed), `standard` (the tier used when the key is unset, at normal priority and rate), and `fast` (about 1.5x faster generation). For ChatGPT auth, `fast` bills at **2.5x** the standard credit rate on GPT-5.6 and GPT-5.5, and 2x on GPT-5.4 (API-key auth pays standard API pricing). Earlier revisions of this file said 2x for all models, which was wrong for the 5.6 family.

204 **Default to `fast`; dial down to `standard` only for an unusually large hands-on task.** `fast` bills 2.5x for about 1.5x speed, which is worth it when a human is waiting on the tokens and the account has quota to spare (for example a second Codex account absorbs the rate). Here the latency saved is worth more than the extra credits. For a rare large task where the 2.5x would bite, dial down with a `standard` V2 profile (`~/.codex/std.config.toml`, selected by `codex -p std`) or `/fast off` mid-session. By default the two background dispatchers stay on standard independently of this policy: `implement-review` and `prun` pass `--ignore-user-config` to their `codex exec` workers for MCP isolation (agent-config#1), so the configured tier does not reach them; `CODEX_DISPATCH_ISOLATE_MCP=off` lifts the isolation and restores the full user config, tier included. The fast default therefore governs interactive and MCP sessions, exactly where the latency is worth paying for. Hardcoding `fast` into the isolated dispatch path is deliberately avoided, because it would fail every round for a consumer whose account lacks the tier. `fast` is the current config spelling and maps to the request value `priority`; a config already reading `priority` is the same tier.

205 Codex does **not** validate `model_reasoning_effort` client-side. An unknown value reaches the service, which rejects the first turn with HTTP `400` and exits nonzero, so a typo fails loudly rather than degrading silently. **Do not treat that error's enumerated list as complete**: it names only `none` / `minimal` / `low` / `medium` / `high` / `xhigh`, yet `max` and `ultra` are also accepted on GPT-5.6.

206 **`ultra` is not simply more reasoning than `max`.** For GPT-5.6 Sol the single-agent reasoning ladder ends at `max`; `ultra` keeps that same maximum reasoning and additionally switches the harness into automatic task delegation (the rollout records `multi_agent_mode: proactive` for `ultra` versus `explicitRequestOnly` for `max`). GPT-5.6 Terra also exposes `ultra`; GPT-5.6 Luna tops out at `max`. Use `max` as the shared default, and choose `ultra` only when proactive delegation is actually wanted. Confirm which mode landed by reading `~/.codex/sessions/**/rollout-*.jsonl` (`payload.model`, `payload.effort`, and the collaboration-mode fields) rather than trusting the config file. `service_tier` is not recorded there.

207 The `implement-review` dispatcher keeps `xhigh` (`CODEX_DISPATCH_REASONING`) as a deliberate cross-model compatibility default, because models older than GPT-5.6 reject `max` and `ultra`; that is a compatibility floor, not a claim that `xhigh` is full strength.

208 `conversationDetailMode = "DEFAULT"` keeps Codex terminal output concise; avoid `STEPS_PROSE` / Coding mode unless you explicitly want command-level progress shown during turns.

209- **Windows PATH note**: Claude Code launches MCP servers through bash, not cmd or PowerShell, so `.cmd` wrappers and `$env:APPDATA` do not work. If `codex` is not on bash PATH, register with the full path using forward slashes and NO `.cmd` extension (e.g., `C:/Users/<you>/AppData/Roaming/npm/codex`). Run `where codex` (cmd) or `Get-Command codex` (PowerShell) to find it.

210- **`approval_policy=never` rationale**: without it, MCP shell commands trigger "MCP server requests your input" dialogs in Claude Code. With it, failures return to Codex/Claude as tool errors. Claude Code's PreToolUse hooks still gate the outer MCP tool call. For interactive Codex terminal sessions (NOT MCP), prefer `approval_policy = "on-request"` in `config.toml`.

211- **Windows recommendation: prefer the terminal path over MCP.** On Windows (11 Build 26200+), MCP has residual rough edges (approval prompts, AV false positives). The terminal path (Codex interactive window for reviews) avoids both. Prefer terminal on Windows; MCP is smoother on macOS/Linux.

212

213

214## Writing Defaults

215

216- Use scientifically accessible language.

@@ −307 @@

307- Do not conclude that Python is unavailable just because `python`, `python3`, or `py` fails in `PATH`; those may resolve to shims, store aliases, or the wrong interpreter. Inspect common environment managers (Miniforge/Conda, pyenv, uv, venv) before reporting Python as missing.

308- If the user's fork sets a preferred Python interpreter path in `AGENTS.local.md`, use that first.

309- GitHub CLI (`gh`) is used for PR and issue workflows. If `gh` is not found, remind the user to install it (`winget install GitHub.cli` on Windows, `brew install gh` on macOS, `gh` from the distro package manager on Linux) and authenticate with `gh auth login`.

310

311- **Claude Code installation**: Prefer the **native installer**. Migrate off npm and winget when possible.

312 - macOS: `curl -fsSL https://claude.ai/install.sh | sh`

313 - Windows (PowerShell, no admin): `irm https://claude.ai/install.ps1 | iex` (requires Git for Windows)

@@ −315 @@

315 - Native installs auto-update in the background by default. Use `/config` inside Claude Code to set the release channel (`latest` or `stable`). Run `claude doctor` to inspect updater status, and `claude update` to force an immediate update check.

316 - To disable auto-updates, set `DISABLE_AUTOUPDATER=1` in the environment or add `"env": {"DISABLE_AUTOUPDATER": "1"}` to `~/.claude/settings.json`. The env var takes precedence regardless of other flags.

317- **Claude Code effort level**: As of Claude Code v2.1.111, the `/effort` slider exposes five levels: `low`, `medium`, `high`, `xhigh`, `max`. The persisted `effortLevel` key in `settings.json` accepts `low`, `medium`, `high`, and `xhigh` (v2.1.111 added `xhigh` as a valid persisted value). `max` remains session-only: selecting `max` via `/effort` silently does not persist. To get `max` as a persistent default across every project and session, set the env var `CLAUDE_CODE_EFFORT_LEVEL=max` in `~/.claude/settings.json` under `"env"`. The shared `user/settings.json` in this repo sets the env var, and bootstrap merges it into `~/.claude/settings.json`, so running bootstrap once on any consuming project lands the user-level default. Runtime precedence: managed policy > `CLAUDE_CODE_EFFORT_LEVEL` env var > persisted `effortLevel` (local > project > user) > Claude Code's built-in default. When the env var is set, it outranks `--effort` at launch and `/effort` inside a session; the slash command prints a warning that the env var is overriding the live effort. When the env var is unset, `--effort <level>` at launch is a session-only override, `/effort low|medium|high|xhigh` updates the persisted user setting, and `/effort max` is session-only.

318

319

320## Local Skills Precedence

321

yzhao062/anywhere-agents · CLAUDE.md

@@ +1 @@

1<!--

2GENERATED FILE -- do not edit by hand.

4This file is regenerated from AGENTS.md by scripts/generate_agent_configs.py.

5Bootstrap re-runs the generator on every session, so edits here are lost.

7Precedence for agent rule files (most specific wins):

8 1. CLAUDE.local.md your per-agent, per-project overrides

9 2. AGENTS.local.md your cross-agent, per-project overrides

10 3. CLAUDE.md generated from AGENTS.md (this file)

11 4. AGENTS.md upstream baseline

13To customize just for Claude Code in this project, create CLAUDE.local.md

14(the generator never touches it). To customize for every agent in this

15project, edit AGENTS.local.md. To change upstream rules for everyone,

16edit AGENTS.md in your fork.

17-->

19

21> **Claude Code / Codex / other agents -- determine your context before proceeding:**

@@ +196 @@

196- If the `superpowers` plugin is active, the router operates during the execution phase. Superpowers handles the outer workflow (brainstorm, plan, execute, verify); the router handles inner dispatch to the right domain skill.

197- If routing is ambiguous (multiple skills could apply), state the detected context and proposed skill, then ask the user to confirm.

198

199## Writing Defaults

200

201- Use scientifically accessible language.

@@ +292 @@

292- Do not conclude that Python is unavailable just because `python`, `python3`, or `py` fails in `PATH`; those may resolve to shims, store aliases, or the wrong interpreter. Inspect common environment managers (Miniforge/Conda, pyenv, uv, venv) before reporting Python as missing.

293- If the user's fork sets a preferred Python interpreter path in `AGENTS.local.md`, use that first.

294- GitHub CLI (`gh`) is used for PR and issue workflows. If `gh` is not found, remind the user to install it (`winget install GitHub.cli` on Windows, `brew install gh` on macOS, `gh` from the distro package manager on Linux) and authenticate with `gh auth login`.

295- **Claude Code installation**: Prefer the **native installer**. Migrate off npm and winget when possible.

296 - macOS: `curl -fsSL https://claude.ai/install.sh | sh`

297 - Windows (PowerShell, no admin): `irm https://claude.ai/install.ps1 | iex` (requires Git for Windows)

@@ +299 @@

299 - Native installs auto-update in the background by default. Use `/config` inside Claude Code to set the release channel (`latest` or `stable`). Run `claude doctor` to inspect updater status, and `claude update` to force an immediate update check.

300 - To disable auto-updates, set `DISABLE_AUTOUPDATER=1` in the environment or add `"env": {"DISABLE_AUTOUPDATER": "1"}` to `~/.claude/settings.json`. The env var takes precedence regardless of other flags.

301- **Claude Code effort level**: As of Claude Code v2.1.111, the `/effort` slider exposes five levels: `low`, `medium`, `high`, `xhigh`, `max`. The persisted `effortLevel` key in `settings.json` accepts `low`, `medium`, `high`, and `xhigh` (v2.1.111 added `xhigh` as a valid persisted value). `max` remains session-only: selecting `max` via `/effort` silently does not persist. To get `max` as a persistent default across every project and session, set the env var `CLAUDE_CODE_EFFORT_LEVEL=max` in `~/.claude/settings.json` under `"env"`. The shared `user/settings.json` in this repo sets the env var, and bootstrap merges it into `~/.claude/settings.json`, so running bootstrap once on any consuming project lands the user-level default. Runtime precedence: managed policy > `CLAUDE_CODE_EFFORT_LEVEL` env var > persisted `effortLevel` (local > project > user) > Claude Code's built-in default. When the env var is set, it outranks `--effort` at launch and `/effort` inside a session; the slash command prints a warning that the env var is overriding the live effort. When the env var is unset, `--effort <level>` at launch is a session-only override, `/effort low|medium|high|xhigh` updates the persisted user setting, and `/effort max` is session-only.

302

303## Local Skills Precedence

304

@@ −1 +1 @@

1+<!--

2+GENERATED FILE -- do not edit by hand.

4+This file is regenerated from AGENTS.md by scripts/generate_agent_configs.py.

5+Bootstrap re-runs the generator on every session, so edits here are lost.

7+Precedence for agent rule files (most specific wins):

8+ 1. CLAUDE.local.md your per-agent, per-project overrides

9+ 2. AGENTS.local.md your cross-agent, per-project overrides

10+ 3. CLAUDE.md generated from AGENTS.md (this file)

11+ 4. AGENTS.md upstream baseline

12+

13+To customize just for Claude Code in this project, create CLAUDE.local.md

14+(the generator never touches it). To customize for every agent in this

15+project, edit AGENTS.local.md. To change upstream rules for everyone,

16+edit AGENTS.md in your fork.

17+-->

18+

119

220

321 > **Claude Code / Codex / other agents -- determine your context before proceeding:**

@@ −178 +196 @@

178196 - If the `superpowers` plugin is active, the router operates during the execution phase. Superpowers handles the outer workflow (brainstorm, plan, execute, verify); the router handles inner dispatch to the right domain skill.

179197 - If routing is ambiguous (multiple skills could apply), state the detected context and proposed skill, then ask the user to confirm.

180198

181−

182−## Codex MCP Integration

183−

184−- Codex can run as an MCP server callable from Claude Code. Register at user scope (NOT project scope; project-scoped entries do not propagate across directories):

185− ```

186− claude mcp add codex -s user -- codex mcp-server -c approval_policy=never

187− ```

188− Writes to `~/.claude.json` `mcpServers`; session restart required for `/mcp` to pick it up. Available MCP tools after registration: `codex` (new prompt) and `codex-reply` (continue an existing session).

189−- Prerequisites: Node.js + Codex CLI (`npm install -g @openai/codex`) + `OPENAI_API_KEY`.

190−- **Recommended Codex defaults** (added to `~/.codex/config.toml` on POSIX or `%USERPROFILE%\.codex\config.toml` on Windows; the MCP server reads the same file as interactive sessions):

191− ```toml

192− model = "gpt-5.6-sol"

193− model_reasoning_effort = "max"

194− service_tier = "fast"

195−

196− [features]

197− fast_mode = true

198−

199− [desktop]

200− conversationDetailMode = "DEFAULT"

201− ```

202− **GPT-5.6 requires Codex CLI 0.144.0 or newer.** The GPT-5.6 family (`gpt-5.6-sol` flagship, `gpt-5.6-terra` mid, `gpt-5.6-luna` cheapest) is rejected by older builds with a hard `400`: `The 'gpt-5.6-sol' model requires a newer version of Codex.` Verified live: 0.142.5 and 0.143.0 fail, 0.144.0 and 0.144.1 work. If the model errors, run `npm install -g @openai/codex@latest` first. `gpt-5.6-sol` is Codex's own recommended default and suits the gatekeeper role; use `gpt-5.6-terra` for high-fan-out work (e.g. `prun` dispatch) where throughput beats peak capability.

203− **`service_tier` buys latency, never quality.** It selects the serving queue only: the model, its weights, and `model_reasoning_effort` are identical across tiers, so `standard` returns the same answer `fast` would, just generated more slowly. The three tiers are `flex` (lower-priority queue, roughly half rate, availability not guaranteed), `standard` (the tier used when the key is unset, at normal priority and rate), and `fast` (about 1.5x faster generation). For ChatGPT auth, `fast` bills at **2.5x** the standard credit rate on GPT-5.6 and GPT-5.5, and 2x on GPT-5.4 (API-key auth pays standard API pricing). Earlier revisions of this file said 2x for all models, which was wrong for the 5.6 family.

204− **Default to `fast`; dial down to `standard` only for an unusually large hands-on task.** `fast` bills 2.5x for about 1.5x speed, which is worth it when a human is waiting on the tokens and the account has quota to spare (for example a second Codex account absorbs the rate). Here the latency saved is worth more than the extra credits. For a rare large task where the 2.5x would bite, dial down with a `standard` V2 profile (`~/.codex/std.config.toml`, selected by `codex -p std`) or `/fast off` mid-session. By default the two background dispatchers stay on standard independently of this policy: `implement-review` and `prun` pass `--ignore-user-config` to their `codex exec` workers for MCP isolation (agent-config#1), so the configured tier does not reach them; `CODEX_DISPATCH_ISOLATE_MCP=off` lifts the isolation and restores the full user config, tier included. The fast default therefore governs interactive and MCP sessions, exactly where the latency is worth paying for. Hardcoding `fast` into the isolated dispatch path is deliberately avoided, because it would fail every round for a consumer whose account lacks the tier. `fast` is the current config spelling and maps to the request value `priority`; a config already reading `priority` is the same tier.

205− Codex does **not** validate `model_reasoning_effort` client-side. An unknown value reaches the service, which rejects the first turn with HTTP `400` and exits nonzero, so a typo fails loudly rather than degrading silently. **Do not treat that error's enumerated list as complete**: it names only `none` / `minimal` / `low` / `medium` / `high` / `xhigh`, yet `max` and `ultra` are also accepted on GPT-5.6.

206− **`ultra` is not simply more reasoning than `max`.** For GPT-5.6 Sol the single-agent reasoning ladder ends at `max`; `ultra` keeps that same maximum reasoning and additionally switches the harness into automatic task delegation (the rollout records `multi_agent_mode: proactive` for `ultra` versus `explicitRequestOnly` for `max`). GPT-5.6 Terra also exposes `ultra`; GPT-5.6 Luna tops out at `max`. Use `max` as the shared default, and choose `ultra` only when proactive delegation is actually wanted. Confirm which mode landed by reading `~/.codex/sessions/**/rollout-*.jsonl` (`payload.model`, `payload.effort`, and the collaboration-mode fields) rather than trusting the config file. `service_tier` is not recorded there.

207− The `implement-review` dispatcher keeps `xhigh` (`CODEX_DISPATCH_REASONING`) as a deliberate cross-model compatibility default, because models older than GPT-5.6 reject `max` and `ultra`; that is a compatibility floor, not a claim that `xhigh` is full strength.

208− `conversationDetailMode = "DEFAULT"` keeps Codex terminal output concise; avoid `STEPS_PROSE` / Coding mode unless you explicitly want command-level progress shown during turns.

209−- **Windows PATH note**: Claude Code launches MCP servers through bash, not cmd or PowerShell, so `.cmd` wrappers and `$env:APPDATA` do not work. If `codex` is not on bash PATH, register with the full path using forward slashes and NO `.cmd` extension (e.g., `C:/Users/<you>/AppData/Roaming/npm/codex`). Run `where codex` (cmd) or `Get-Command codex` (PowerShell) to find it.

210−- **`approval_policy=never` rationale**: without it, MCP shell commands trigger "MCP server requests your input" dialogs in Claude Code. With it, failures return to Codex/Claude as tool errors. Claude Code's PreToolUse hooks still gate the outer MCP tool call. For interactive Codex terminal sessions (NOT MCP), prefer `approval_policy = "on-request"` in `config.toml`.

211−- **Windows recommendation: prefer the terminal path over MCP.** On Windows (11 Build 26200+), MCP has residual rough edges (approval prompts, AV false positives). The terminal path (Codex interactive window for reviews) avoids both. Prefer terminal on Windows; MCP is smoother on macOS/Linux.

212−

213−

214199 ## Writing Defaults

215200

216201 - Use scientifically accessible language.

@@ −307 +292 @@

307292 - Do not conclude that Python is unavailable just because `python`, `python3`, or `py` fails in `PATH`; those may resolve to shims, store aliases, or the wrong interpreter. Inspect common environment managers (Miniforge/Conda, pyenv, uv, venv) before reporting Python as missing.

308293 - If the user's fork sets a preferred Python interpreter path in `AGENTS.local.md`, use that first.

309294 - GitHub CLI (`gh`) is used for PR and issue workflows. If `gh` is not found, remind the user to install it (`winget install GitHub.cli` on Windows, `brew install gh` on macOS, `gh` from the distro package manager on Linux) and authenticate with `gh auth login`.

310−

311295 - **Claude Code installation**: Prefer the **native installer**. Migrate off npm and winget when possible.

312296 - macOS: `curl -fsSL https://claude.ai/install.sh | sh`

313297 - Windows (PowerShell, no admin): `irm https://claude.ai/install.ps1 | iex` (requires Git for Windows)

@@ −315 +299 @@

315299 - Native installs auto-update in the background by default. Use `/config` inside Claude Code to set the release channel (`latest` or `stable`). Run `claude doctor` to inspect updater status, and `claude update` to force an immediate update check.

316300 - To disable auto-updates, set `DISABLE_AUTOUPDATER=1` in the environment or add `"env": {"DISABLE_AUTOUPDATER": "1"}` to `~/.claude/settings.json`. The env var takes precedence regardless of other flags.

317301 - **Claude Code effort level**: As of Claude Code v2.1.111, the `/effort` slider exposes five levels: `low`, `medium`, `high`, `xhigh`, `max`. The persisted `effortLevel` key in `settings.json` accepts `low`, `medium`, `high`, and `xhigh` (v2.1.111 added `xhigh` as a valid persisted value). `max` remains session-only: selecting `max` via `/effort` silently does not persist. To get `max` as a persistent default across every project and session, set the env var `CLAUDE_CODE_EFFORT_LEVEL=max` in `~/.claude/settings.json` under `"env"`. The shared `user/settings.json` in this repo sets the env var, and bootstrap merges it into `~/.claude/settings.json`, so running bootstrap once on any consuming project lands the user-level default. Runtime precedence: managed policy > `CLAUDE_CODE_EFFORT_LEVEL` env var > persisted `effortLevel` (local > project > user) > Claude Code's built-in default. When the env var is set, it outranks `--effort` at launch and `/effort` inside a session; the slash command prints a warning that the env var is overriding the live effort. When the env var is unset, `--effort <level>` at launch is a session-only override, `/effort low|medium|high|xhigh` updates the persisted user setting, and `/effort max` is session-only.

318−

319302

320303 ## Local Skills Precedence

321304