Global configuration reference
Setup is in Global configuration. This page holds the per-key and per-tool detail, and the list of files sync --global writes.
Shared names
A project skill or agent can share its name with one in the home. Sync writes both, and each tool decides which one it loads.
sync and doctor print one warning per shared name. It names each target where one copy hides the other, which copy wins, and the fix:
! .agnostic-ai/skills/gh-issue/SKILL.md: skill "gh-issue" also exists in ~/.agnostic-ai/skills/gh-issue/SKILL.md with different content; claude loads the global one, which exists only on this machine, gemini loads this one; to load both, rename the global one (such as gh-issue-personal), or delete it to drop it, then run `agnostic-ai sync --global`; project sync cannot select this skill instead on claude
Why sync keeps both copies:
- Claude Code, Cline, and Amp document no project setting that picks the project copy over a home skill and keeps the other home skills.
- Amp's
amp.skills.disableGlobalAgentsSkillsturns off every skill in the global agents folders. - So sync explains the limit and leaves your home files alone. Doctor reports it even when sync warnings are off.
- A winning global copy changes what you run, not what others run from the repository.
- When only project copies win, the warning says the global one is unused here. When both copies match, it says to delete one before they drift apart.
The check covers these targets:
| Target | Skill with the same name | Agent with the same name |
|---|---|---|
| Amp | Global wins when both sync amp: ~/.agents/skills/ masks .agents/skills/ (skills) | No global agents |
| Claude Code | Global wins (skills) | Project wins (subagents) |
| Cline | Global wins (skills) when the project syncs cline and the home syncs cline, or any target that writes ~/.agents/skills/, which Cline also reads (config) | Not checked |
| Codex | Both can appear in skill selectors, so no warning (skills) | Not checked |
| Gemini CLI | Project wins (skills) | Not checked |
Sync and doctor do not check other tools, though some document what happens:
- Kiro prefers workspace skills over global skills.
- Qoder IDE documents project skills taking priority over user skills. Qoder CLI documents user skills taking priority over project skills.
- Warp prefers home skills, then higher directories, when it resolves names in the background. Its slash-command menu shows all matches, and a plain-language request gives the agent every match in scope with its path.
Which pairs the check compares
- Targets that both the project and the home's
targetswrite. A spec whosetarget,targets, ortargets-excludeleaves one of them out is skipped. - Claude Code skill names match ignoring case, spacing, invisible characters, and fullwidth forms. Other targets compare names exactly.
- A spec shared through a link is not a clash. Neither is a project that is the home.
To resolve a clash:
- Layer on purpose: give the project spec its own name, such as a
gh-issue-projectskill beside a globalgh-issue. Both then load everywhere. - Keep one name in both places: list it in
sync.allow-global-names. - Silence every shared name: set
sync.global-name-clash: ignore.
Default model and effort
A settings spec in the home sets each tool's default model and effort in its user settings file. model and effort each take one string for every target, or a per-target map with an optional default:
# ~/.agnostic-ai/settings/defaults.yaml
model:
claude: opus
codex: gpt-6-luna
effort:
claude: high
codex: high
| Target | File | Keys |
|---|---|---|
| codex | ~/.codex/config.toml | model, model_reasoning_effort |
| claude | ~/.claude/settings.json | model, effortLevel, permissions.defaultMode, permissions.allow, ask, deny |
| codebuddy | ~/.codebuddy/settings.json | model, reasoningEffort, permissions.defaultMode, permissions.allow, ask, deny |
| copilot | ~/.copilot/settings.json | model, effortLevel |
| qoder | ~/.qoder/settings.json | model.name, model.reasoningEffort |
| qwen | ~/.qwen/settings.json | model.name, model.reasoningEffort |
| vibe | ~/.vibe/config.toml | active_model |
| kimi | ~/.kimi-code/config.toml | default_model, default_plan_mode, telemetry |
| gemini | ~/.gemini/settings.json | model.name |
| augment | ~/.augment/settings.json | defaultModel, defaultThinkingLevel (Auggie 1.x) |
- Targets not in the table raise a coverage note for
modelandeffort. So doesefforton Gemini and Kimi Code. - Augment also takes
x-augmentkeys, such asshell. - A dotted key is a nested JSON object, except for Kiro CLI's literal dotted keys. For
model.name, sync setsnameinsidemodeland leaves the other keys alone.
Details: accepted effort values
| Target | Accepted effort values |
|---|---|
| Claude | low, medium, high, xhigh |
| Copilot | none, minimal, low, medium, high, xhigh, max (each model accepts a subset) |
| Qoder | disabled, off, none, low, medium, high, xhigh, max |
| Augment | off, minimal, low, medium, high, xhigh |
| Qwen | low, medium, high, xhigh, max (each provider maps the value to its active model) |
| Codex | Any string |
| CodeBuddy Code | See native fields and limits |
lint --global (LINT014) and validate --global flag a value a target cannot take.
Claude Code and effortLevel:
~/.claude/settings.jsoneffortLevelis read on Opus 5, Fable 5.1, and earlier models only.- Opus 5.5 and later models ignore it. They need a level saved per model with
/effort. sync --globalwrites the key and prints a note.- In project settings,
effortLevelapplies to every model.
Permissions
Set Claude Code's starting permission mode in a home settings spec:
# ~/.agnostic-ai/settings/defaults.yaml
permissions:
default-mode: acceptEdits
sync --global --only claudewritespermissions.defaultModein~/.claude/settings.json, or underCLAUDE_CONFIG_DIR.- Accepted values:
default,manual,acceptEdits,plan,auto,dontAsk,bypassPermissions. - A later settings spec wins.
- Removing the field removes the managed mode, unless you changed it by hand.
- Claude's
autoandbypassPermissionsneed user, managed, or session settings (Claude's mode reference).
Home permissions.allow, ask, and deny rules, and the same lists under x-claude.permissions, merge into ~/.claude/settings.json rule by rule.
- Claude Code saves standing approvals to the project's
.claude/settings.local.json, which global import does not read (Claude's settings scopes). - CodeBuddy Code also merges user permission lists and starting modes (native limits).
- A
permissionsfield on any other target raises a coverage note. For Codex, setx-codex.approval_policyandx-codex.sandbox_modeinstead.
Details: how permission rules merge
- Sync appends each missing rule after the rules already there, and adopts a rule already there.
- Sync records added and adopted rules in
state/global.json. - Dropping a rule from the specs removes it, including a rule you wrote before adoption. Other rules keep their order.
--checkfails while a spec rule is missing or a dropped one remains.--planand--dry-runlist each rule added or removed.import --global claudecopies user-level rules intosettings/permissions-claude.yaml, so they reach your other machines.
Other settings
session-retention-dayssets how many days transcripts are kept, for Claude Code, CodeBuddy Code, Gemini CLI, and Qoder CLI (session retention).voiceconfigures voice dictation for tools with a native setting (voice dictation).
Which value wins
Each item wins over the one before it:
settings/*.yamlin the home.local/settings/*.yaml. A same-named file merges into the shared one field by field. A new file comes after the shared ones, so itsmodelandeffortwin.- The project tier: a project's settings file, such as
.codex/config.tomlor.claude/settings.json, wins by the tool's own settings order. - An agent's own
modelandeffort, for that agent. - The tool's flag for one run, such as
codex -morclaude --model.
agnostic-ai explain --global settings/defaults.yaml names the file and key each target gets.Details: how sync edits settings keys
"env": {}./model picker saves to config.toml. --backup overwrites the key and keeps <path>.bak.--dry-run lists each key a write sets or removes. --check fails on a changed key.x-<target> block sets that target's own keys in the same file. Nested objects merge leaf by leaf.x-claude key wins over the portable field it shares a key with.null drops an earlier key.x-codex.notify, to ~/.codex/config.toml.profiles, x-claude.hooks, and x-claude.permissions keys other than allow, ask, and deny raise a coverage note.x-codex into .codex/config.toml.
Approvals
approvals sets what happens when a tool wants permission for a tool call:
| Mode | What happens |
|---|---|
ask | The tool shows its prompt. The default. |
review | The tool's own reviewer model decides routine requests. The rest still ask. |
yolo | Each request is approved once, unless a fixed always-ask rule matches. |
# $AGNOSTIC_AI_HOME/agnostic-ai.yaml or $AGNOSTIC_AI_HOME/local/agnostic-ai.yaml
approvals:
mode: ask # ask | review | yolo
tools: # per tool, replaces mode
codex: review
projects: # per project folder, replaces mode and tools
~/Code/sandbox: yolo
always-ask: # extra patterns, added to the fixed list
- "Bash(make deploy*)"
reviewandyoloare read only from the home config. A cloned repository, a pull request, or the agent itself can write a project's files, so a project'sagnostic-ai.yamloragnostic-ai.local.yamlmay setapprovals.mode: askand nothing else. Any otherapprovalskey there is ignored, andvalidateandlintreport it as LINT064.- An
approvalsblock inlocal/agnostic-ai.yamlreplaces the shared block whole, exceptalways-ask: the patterns of both files add up. - A
projectskey is an absolute path or one under~, the home folder. The deepest folder that holds the session wins; links are resolved, and on macOS and Windows case is ignored. Two keys for one folder take the stricter mode. - The strictest source wins, in this order:
AGNOSTIC_AI_APPROVALS=askin the session's environment, a project file that saysask,projects,tools,mode. Any value of the environment variable meansask: it can only tighten. - A config without
approvalsbehaves asask.$AGNOSTIC_AI_HOMEmust be an absolute path for approvals to read it. - Only Claude Code and Codex carry out
yolo, through a hook thatbuiltins: [approvals]andsync --globalinstall (Approvals). Only the tools in the review table carry outreview. Every other tool falls back toask, andapprovals statussays so.
Review through the tool's own reviewer
When approvals.tools.<tool>, or approvals.mode without it, says review, sync --global turns on the tool's own reviewer in its user settings:
| Tool | Reviewer | Key sync --global writes |
|---|---|---|
| Claude Code | Auto mode | permissions.defaultMode: "auto" in ~/.claude/settings.json |
| CodeBuddy | Auto mode, an AI reviewer; not run by us | permissions.defaultMode: "auto" in ~/.codebuddy/settings.json |
| Codex | Auto-review | approvals_reviewer = "auto_review" in ~/.codex/config.toml |
Cursor (cursor-agent only) | Auto-review, a server classifier | approvalMode: "auto-review" in ~/.cursor/cli-config.json |
Devin CLI (windsurf) | Smart mode, a fast model; not run by us | permission_mode: "smart" in ~/.config/devin/config.json (%APPDATA%\devin\config.json on Windows) |
| Qoder | Auto mode, a two-stage classifier; not run by us | general.defaultPermissionMode: "auto" in ~/.qoder/settings.json |
| Vibe | Smart-approve, a classifier; not run by us | default_agent = "smart-approve" in ~/.vibe/config.toml |
| Qwen Code | Auto mode, an LLM classifier; not run by us | tools.approvalMode: "auto" in ~/.qwen/settings.json |
- A home settings spec that sets the same key wins:
permissions.default-modewhere the tool maps it, otherwise the key underx-<tool>, such asx-codex.approvals_reviewer. A value set outside agnostic-ai stays as it is, andsync --globalwarns that the reviewer stays off. - Remove
reviewand runsync --globalagain, and the key goes.approvals askalone does not remove it. - The key sits in a user file, so it applies in every folder. A
projectsentry orAGNOSTIC_AI_APPROVALS=askcannot turn the reviewer off for one folder or session;approvals statusnotes it there. A project sync never writes these keys. - Codex Auto-review answers only prompts Codex would show. With
approval_policy = "never"there are none, so the reviewer never runs;approvals statussays so when~/.codex/config.tomlsets it. It does not read a trusted project's.codex/config.toml, which can set either key too. - Qwen Code already runs auto mode in a trusted folder when
tools.approvalModeis unset, soaskalone does not bring its prompts back;approvals statussays so. Setx-qwen.tools.approvalMode: defaultin a home settings spec to see them. Qwen Code asks anyway in an untrusted folder and with--bareor--safe-mode, and a project's.qwen/settings.jsoncan set the same key. Checked against the Qwen Code 0.28.0 package. - CodeBuddy takes
defaultMode: "auto"only from user settings and the command line; a project file cannot grant it. It falls back todefaultwhenpermissions.disableAutoModeis"disable"or auto mode is unavailable, andapprovals statusnotes the first.sync --globalwrites~/.codebuddy/settings.jsoneven whenCODEBUDDY_CONFIG_DIRmoves CodeBuddy's settings elsewhere; status notes that too. Checked against the CodeBuddy 2.185.0 package and its permission-modes page. - cursor-agent reads
cli-config.jsonfromCURSOR_CONFIG_DIR, else$XDG_CONFIG_HOME/cursor, else~/.cursor, andsync --globalfollows the same order. cursor-agent rewrites that file itself, so sync owns onlyapprovalModethere. cursor-agent writesapprovalMode: "allowlist"as its own default, so review replaces that value and gives the key back when review goes; any other value set by hand stays.x-cursor.approvalModein a home settings spec wins and must beallowlist,unrestrictedorauto-review, since cursor-agent sets a file with any other value aside and starts over.CURSOR_CONFIG_DIRandXDG_CONFIG_HOMEmust be absolute paths. Auto-review needs a classifier-capable model and team permission, or cursor-agent falls back to its allowlist. The Cursor desktop app keeps its own setting, andapprovals statussays to turn on Auto-review there. Checked against cursor-agent 2026.11.11, which kept the key when it rewrote the file. - Devin CLI reads
permission_modeonly from the user config, so a project cannot set it.--permission-modereplaces it for one launch. Devin's docs also showDEVIN_PERMISSION_MODE=smart devin, andapprovals statusnotes a set variable; that the variable wins over the file is our reading, not stated. Anullvalue means normal, so review replaces it. Your organization's policy can remove Smart mode, and sandbox sessions do not offer it; the docs do not say what Devin does with the key then.approvals statusreportsdangerousas approving every call. Sync owns onlypermission_modein that file;x-windsurf.permission_modein a home settings spec wins and must benormal,accept-edits,smartordangerous. Your owndenyandaskrules still come first. From the Devin CLI configuration and permissions pages; Devin CLI is not installed here. - Qoder reads
general.defaultPermissionModefrom every settings layer, so a project's.qoder/settings.jsoncan set it too, and an untrusted folder starts indefault, as does a session with no classifier model available. An oldertools.approvalModekey counts as the user's mode, so review leaves it. Checked against the Qoder CLI 1.1.93 package. - Vibe takes a
default_agentthat a person sets as an opt-in, so smart-approve starts even before the mode reaches Vibe's mode picker. An organization can still exclude it, and a trusted project's.vibe/config.toml,VIBE_DEFAULT_AGENT, an admin config, or--agentreplaces the user file's value. In the user file,x-vibecannot setdefault_agent, so only a hand-set value wins; Vibe can also writedefault_agent = "ask"there itself whendisabled_agentslistsaccept-edits. Withbypass_tool_permissions = true, Vibe approves every call and the classifier never runs;approvals statusnotes it and a setVIBE_DEFAULT_AGENT. Checked against the mistral-vibe 3.1.3 package. - A running session keeps its mode until you switch it in the tool (Shift+Tab in Claude Code). A new session reads the new settings.
- agnostic-ai logs no decision the reviewer makes. Each tool keeps its own record, and each review costs the tool's own model calls.
Run approvals status to see the mode and route per tool, and approvals ask to show every prompt again.
MCP servers
MCP specs in the home's mcps/ install servers in each supported tool's user MCP file, using the same format as project servers:
| Target | File | Where |
|---|---|---|
| claude | ~/.claude.json ($CLAUDE_CONFIG_DIR/.claude.json when set) | top-level mcpServers.<name> |
| codex | ~/.codex/config.toml | [mcp_servers.<name>] table |
| codebuddy | ~/.codebuddy/.mcp.json | mcpServers.<name>; legacy precedence and native limits |
| vibe | ~/.vibe/config.toml | [[mcp_servers]], keyed by name |
| kimi | ~/.kimi-code/mcp.json | mcpServers.<name>, retaining disabled servers |
| cursor | ~/.cursor/mcp.json | mcpServers.<name> |
| copilot | ~/.copilot/mcp-config.json | mcpServers.<name>, with tools: ["*"] when the spec sets none |
| gemini | ~/.gemini/settings.json | mcpServers.<name> |
| qoder | ~/.qoder/settings.json | mcpServers.<name> |
| warp | ~/.warp/.mcp.json (Warp app only; the Agent CLI reads its own file) | mcpServers.<name>: {command, args, env, working_directory} or {url, headers} |
| augment | ~/.augment/settings.json | mcpServers.<name> |
| antigravity | ~/.gemini/config/mcp_config.json | mcpServers.<name>: {command, args, env, cwd} or {serverUrl, headers}, with optional disabled |
The Tools page in serve --global lists servers that have no home spec and were not written by sync. Each row has the import --global <target> command that creates its spec (serve).
OpenHands has no user MCP file sync can write. Sync prints a note that points at Agent Canvas Customize > MCP Servers. It also removes the servers an earlier sync recorded as its own in ~/.openhands/mcp.json (OpenHands MCP).Details: how sync edits MCP servers
--backup overwrites it.~/.claude.json, sync edits only its own mcpServers entries and creates a missing file at 0600.~/.claude.json changed after sync read it, sync stops without writing. Run it again.disabled: true stays out of the Augment, Claude, Cursor, Copilot, and Warp user files, where a listed server is live in every project.disabled: true.CLAUDE_CONFIG_DIR or another root variable moves a file, the next sync removes its entries from the old one.
Native discovery and shared paths
Discovery limits
- Copilot's path is for its CLI.
- OpenHands discovery applies to local conversations.
- Devin custom profiles are experimental.
- Trae needs Settings > Beta > Subagents > Enable Subagents Directory.
Configuration roots
CLAUDE_CONFIG_DIR,CODEX_HOME,COPILOT_HOME,CLINE_DIR,QODER_CONFIG_DIR,KIRO_HOME,JUNIE_HOME, andKIMI_CODE_HOMEreplace the matching~/.<tool>/folder.GEMINI_CLI_HOMEis the parent of.gemini/.- Everything under that folder moves together. Paths outside it, such as
~/.agents/skills/, stay put. - Use absolute paths.
Shared paths
Shared paths are written once:
| Path | Tools |
|---|---|
~/.agents/skills/ | codex, windsurf, amp, zed, warp, goose, openhands |
~/.agents/agents/ | goose, openhands |
~/.agents/AGENTS.md | cline, warp |
~/.gemini/GEMINI.md | gemini, antigravity |
If two tools would write different content to one path, the run stops before writing and names the path.
Per-tool notes
Copilot agent effort
- Copilot CLI documents a native profile
reasoningEffortfield, available throughx-copilot.reasoningEffort(agent fields). - Portable agent effort is not mapped to that CLI field.
- A portable agent
effortoflow,medium,high, orxhighgoes tosubagents.agents.<name>.effortLevelin~/.copilot/settings.json. Other values raise a coverage note. - Sync stops when the file has comments, since a rewrite drops them. Rerun with
--backupto rewrite it and keepsettings.json.bak. - Sync also stops when a hand-set
effortLevelhas a different value.
Cursor
- Cursor does not load the home-level
AGENTS.md. - Global sync installs a
sessionStarthook and a script under~/.cursor/hooks/that pass the instructions to Cursor. The script is POSIX shell on macOS and Linux, PowerShell on Windows. - It needs neither agnostic-ai, Python, nor jq, and it adds context without enforcing policy.
- Existing
sessionStartentries stay. - Settings: global sync writes only
approvalModeto cursor-agent'scli-config.json, forapprovals. Otherx-cursorkeys give a note.
OpenCode
disable-model-invocationstays in project and global skills. V2 honors it; V1 does not (OpenCode skills covers native metadata precedence).- V1 reads
~/.claude/CLAUDE.mdonly when~/.config/opencode/AGENTS.mddoes not exist. - The current V2 migration guide documents a
CLAUDE.mdfallback in each directory withoutAGENTS.md, plus~/.claude/CLAUDE.mdwhen the global OpenCodeAGENTS.mdis absent. - V2 chooses per directory, so an
AGENTS.mdat the project root does not hide a nestedCLAUDE.md. - In V2 2.3.1 and later, either
OPENCODE_DISABLE_CLAUDE_CODE_PROMPTorOPENCODE_DISABLE_CLAUDE_CODEdisables everyCLAUDE.mdfallback, both project and global (2.3.1 release notes). - Put OpenCode guidance in its
AGENTS.mdwhen syncing both tools.
Devin CLI and VS Code Copilot
- Both read
~/.claude/by default. Syncing claude plus windsurf or copilot delivers the same instructions through two paths.
Targets left out
No user-level instructions file:
- Aider reaches a home instructions file only through a
read:entry in~/.aider.conf.yml. - Continue's one documented home setting is the
rules:list in theconfig.yamlit rewrites itself. - Jules documents nothing at user level.
- Ellipsis reads only files in the repository.
Hooks reach these tools at user level: Claude Code, CodeBuddy Code, Codex, Gemini, Qoder, Cursor, Augment, Kiro CLI V3, Copilot, Cline SDK/CLI, Grok Build, Kimi Code CLI, Qwen Code, Mistral Vibe, and Goose. The others have no user-level hook output:
- Factory, Devin CLI, Antigravity, and Crush use hook formats that global sync does not write.
- Junie's hooks are Early Access.
- Amp, OpenCode, and Kilo take hooks only as TypeScript plugins. Sync writes them at project level only, for OpenCode (
.opencode/plugins/) and Kilo (.kilo/plugin/). - OpenCode defaults to V1. A hook selects V2 with
x-opencode.plugin-api: v2on macOS and Linux. - On Windows, V2 refuses matching callbacks, so keep the default V1 hooks.
Global output
A dash means global sync writes nothing for that kind.
| Target | Instructions | Rules | Hooks | Skills | Agents | Session retention |
|---|---|---|---|---|---|---|
| claude | ~/.claude/CLAUDE.md | inlined | ~/.claude/settings.json | ~/.claude/skills/<name>/ | ~/.claude/agents/<name>.md | days |
| codebuddy | ~/.codebuddy/CODEBUDDY.md | inlined | ~/.codebuddy/settings.json | ~/.codebuddy/skills/<name>/ | ~/.codebuddy/agents/<name>.md | days |
| cursor | ~/.cursor/AGENTS.md (bridged) | inlined | ~/.cursor/hooks.json | ~/.cursor/skills/<name>/ | ~/.cursor/agents/<name>.md | - |
| codex | ~/.codex/AGENTS.md | inlined | ~/.codex/hooks.json | ~/.agents/skills/<name>/ | ~/.codex/agents/<name>.toml | - |
| gemini | ~/.gemini/GEMINI.md | inlined | ~/.gemini/settings.json | ~/.gemini/skills/<name>/ | ~/.gemini/agents/<name>.md | days |
| kimi | ~/.kimi-code/AGENTS.md | inlined | ~/.kimi-code/config.toml | ~/.kimi-code/skills/<name>/ | ~/.kimi-code/agents/<name>.md | - |
| vibe | ~/.vibe/AGENTS.md | inlined | ~/.vibe/hooks.toml | ~/.vibe/skills/<name>/ | ~/.vibe/agents/<name>.toml | - |
| qoder | ~/.qoder/AGENTS.md | inlined | ~/.qoder/settings.json | ~/.qoder/skills/<name>/ | ~/.qoder/agents/<name>.md | days |
| copilot | ~/.copilot/copilot-instructions.md | inlined | ~/.copilot/hooks/agnostic-ai.json | ~/.copilot/skills/<name>/ | ~/.copilot/agents/<name>.agent.md | - |
| cline | ~/.agents/AGENTS.md | inlined | ~/.cline/hooks/<event> | ~/.cline/skills/<name>/ | ~/.cline/agents/<name>.yml | - |
| windsurf | ~/.config/devin/AGENTS.md | inlined | - | ~/.agents/skills/<name>/ | ~/.config/devin/agents/<name>.md | - |
| amp | ~/.config/amp/AGENTS.md | inlined | - | ~/.agents/skills/<name>/ | - | - |
| zed | ~/.config/zed/AGENTS.md; Windows: %APPDATA%\Zed\AGENTS.md | inlined | - | ~/.agents/skills/<name>/ | - | - |
| warp | ~/.agents/AGENTS.md | inlined | - | ~/.agents/skills/<name>/ | - | - |
| opencode | ~/.config/opencode/AGENTS.md | inlined | - | ~/.config/opencode/skills/<name>/ | ~/.config/opencode/agents/<name>.md | - |
| antigravity | ~/.gemini/GEMINI.md | inlined | - | ~/.gemini/config/skills/<name>/ | ~/.gemini/config/agents/<name>/agent.md | - |
| junie | ~/.junie/AGENTS.md | inlined | - | ~/.junie/skills/<name>/ | ~/.junie/agents/<name>.md | - |
| kiro | ~/.kiro/steering/AGENTS.md | inlined | ~/.kiro/hooks/<name>.json | ~/.kiro/skills/<name>/ | ~/.kiro/agents/<name>.md | - |
| crush | ~/.config/crush/CRUSH.md | inlined | - | ~/.config/crush/skills/<name>/ | - | - |
| factory | ~/.factory/AGENTS.md | inlined | - | ~/.factory/skills/<name>/ | ~/.factory/droids/<name>.md | - |
| kilo | ~/.config/kilo/AGENTS.md | inlined | - | ~/.kilo/skills/<name>/ | ~/.config/kilo/agents/<name>.md | - |
| goose | ~/.config/goose/.goosehints | inlined | ~/.agents/plugins/agnostic-ai-global/hooks/hooks.json | ~/.agents/skills/<name>/ | ~/.agents/agents/<name>.md | - |
| openhands | - | - | - | ~/.agents/skills/<name>/ | ~/.agents/agents/<name>.md | - |
| trae | - | - | - | ~/.trae/skills/<name>/ | ~/.trae-cn/agents/<name>.md | - |
| grok | ~/.grok/AGENTS.md | inlined | ~/.grok/hooks/<name>.json | ~/.grok/skills/<name>/ | ~/.grok/agents/<name>.md | - |
| qwen | ~/.qwen/QWEN.md | inlined | ~/.qwen/settings.json | ~/.qwen/skills/<name>/ | ~/.qwen/agents/<name>.md | - |
| augment | - | ~/.augment/rules/<name>.md | ~/.augment/settings.json | ~/.augment/skills/<name>/ | ~/.augment/agents/<name>.md | - |
- MCP servers and settings have their own tables in the reference. Agents use the same formats as project agents (the agent example).
- Rules are inlined into the instructions file, in the same
## Rulesblock as the shared body. - Augment has no user-level instructions file for the CLI, so its
~/.augment/rules/entries are always on. - Existing instruction files keep their personal text and file permissions.
- Sync stops if a file changes while it is preparing the update.
Path notes:
- Paths marked
~/.config/followXDG_CONFIG_HOMEwhen set, except Zed on macOS. - Zed on Linux and FreeBSD prefers
FLATPAK_XDG_CONFIG_HOME(native instruction roots). - Devin agents use
~/.config/devin/agents/on Linux and macOS and%APPDATA%\devin\agents\on Windows.