Supported harnesses
HarnessTap registers 43 agent harnesses today. Each harness declares which resource types it can scan, compose in plugins, and materialize on disk, plus...
HarnessTap registers 43 agent harnesses today. Each harness declares which resource types it can scan, compose in plugins, and materialize on disk, plus default project and global paths. The registry in src/platforms/registry.ts is the source of truth; ht harness list prints the same set at runtime.
For portability caveats (hooks with ${*_PLUGIN_ROOT}, OpenCode server plugins, instruction-only skill emission, and mirror warnings), see Portability limits.
Resource types
HarnessTap separates context-side resources (what the model sees) from environment-side resources (how it runs).
Context-side material resources
These are the atomic resources you scan, curate, attach to plugins, and re-emit during apply:
| Type | Description |
|---|---|
| instructions | Always-on context files (AGENTS.md, CLAUDE.md, .windsurfrules, .github/copilot-instructions.md, …) |
| skills | SKILL.md trees under harness-native skill directories |
| rules | Path-scoped or always-on rules (.cursor/rules/*.mdc, .claude/rules/, .kiro/steering/, …) |
| mcp | MCP server definitions from harness MCP config files |
| permissions | Allow/deny patterns (Claude Code and Codex settings) |
| hooks | Hook event definitions from settings or hooks.json |
| agents | Agent manifest files under harness agents/ directories |
| commands | Static command definitions (markdown, TOML, or manifest pointers) |
Plugin composition adds two attachment kinds on top of material resources:
| Attachment | Role |
|---|---|
| plugin_pin | Lazy link to a host marketplace or local plugin (plugin_pin:name@marketplace); materializes after resource sync or apply --sync-plugins |
| plugin | Nested plugin reference expanded depth-first at apply time |
Environment resources
Environments carry how values that override matching plugin resources during apply (home → plugin default → deck active):
| Type | Description |
|---|---|
| env_var | Plain environment variable key/value pairs |
| model_config | Default model and provider selection |
| permission | Permission allow/deny overrides |
| secret_ref | Indirection to secrets (keychain, env, file) — never embedded in exports |
Only harnesses whose registry entry includes env_vars, model_config, and/or permissions and whose native serializer implements those surfaces receive environment values on disk. Today that means Claude Code and Codex for the full environment trio.
All harnesses whose serializer emits MCP config still receive MCP ${VAR} substitution from the environment cascade at apply time (tokens in MCP env / args). OAuth sessions managed by the host IDE are outside this path — see Environments — MCP authentication limitations.
| Harness | MCP scan/emit | Full env emission | MCP ${VAR} substitution |
|---|---|---|---|
| claude-code | Yes (.mcp.json) | Yes | Yes |
| codex | Yes (config.toml) | Yes | Yes |
| cursor | Yes (.cursor/mcp.json) | No | Yes |
| copilot-cli, github-copilot | Yes | No | Yes |
| opencode, goose, grok-build, antigravity, amazon-q, generic | Yes | No | Yes |
| deepseek-harness | Yes (~/.dsh/cordis.patch.yml home patch) | No | Yes |
| muse-code | Yes (~/.config/muse/settings.json mcp_servers, user-settings only) | No | Yes |
Plugin manifest layouts
scan and plugin-source import recognize these on-disk plugin trees (in addition to per-harness project files):
| Manifest path | Harness family | Imported as |
|---|---|---|
.claude-plugin/plugin.json | Claude Code | claude-plugin |
.claude-plugin/marketplace.json | Claude Code (marketplace root) | marketplace |
.cursor-plugin/plugin.json | Cursor | cursor-plugin |
.cursor-plugin/marketplace.json | Cursor (marketplace root) | marketplace |
.codex-plugin/plugin.json | Codex | codex-plugin |
.github/plugin/plugin.json | GitHub Copilot / Copilot CLI | copilot-plugin |
plugin.json / .goose-plugin/plugin.json / .plugin/plugin.json | Goose (Open Plugins) | goose-plugin |
Scanning a repo with both harness files and a plugin manifest merges both sources automatically. See Portability limits — dual-mode scan.
Plugin install and sync providers
During apply, HarnessTap can install and sync plugins from host install trees for:
| Harness | Provider | Typical install location |
|---|---|---|
| claude-code | Claude Code marketplace / claude plugin | ~/.claude/plugins/ |
| cursor | Inventory + git check/update; marketplace ensure via agent plugin marketplace add (install remains Cursor Customize / /plugin — no agent plugin install) | ~/.cursor/plugins/ |
| goose | goose plugin install (git-backed Open Plugins) | ~/.agents/plugins/ |
| copilot-cli | Copilot CLI marketplace / copilot plugin | ~/.copilot/installed-plugins/ |
| deepseek-harness | dsh plugin --profile web add | $DSH_HOME/profiles/web/ |
Claude Code and Copilot CLI home scan also import installed marketplace plugins as plugin_pin library resources (pins only; use resource sync to materialize children). Claude reads ~/.claude/plugins/installed_plugins.json. Copilot CLI reads ~/.copilot/installed-plugins/<marketplace>/<plugin>/ when ~/.copilot/settings.json or that install tree is present.
Other harnesses still benefit from plugin-source scan and resource sync when you point at an install tree or plugin repo, but do not have an automated install provider yet.
Claude plugin pins and marketplace metadata (plugin show → claude block) apply only when materializing to claude-code.
Serializers
| Tier | Harnesses | Notes |
|---|---|---|
| Native | claude-code, codex, cursor, goose, opencode, github-copilot, copilot-cli, gemini-cli, grok-build, deepseek-harness, muse-code | Dedicated scan/serialize logic |
| Generic | All other registered harnesses | Path-driven serializer driven by registry projectPaths / globalPaths |
Filter native harnesses at the CLI:
ht harness list --supported
ht harness list --format jsonSkill emission modes
Most harnesses emit skills to native skill directories. These harnesses declare skillEmission: instruction-only — skills merge into instructions or rules instead of a separate skill tree:
| Harness | Emission target |
|---|---|
| github-copilot | .github/copilot-instructions.md |
| gemini-cli | Instruction/rules paths per Gemini serializer |
| windsurf | .windsurf/rules/{name}.md |
| cline | .clinerules/{name}.md (or merged rules file) |
| kiro | .kiro/steering/{name}.md |
Cursor additionally honors project cursor_skill_mode (agent-requested, always-on, agents-skills). Inspect with ht harness project status --project . --format json.
Agent / subagent bridging
Harnesses with a delegated subagent model normalize into a shared canonical shape (description, instruction body, model, reasoning_effort, sandbox/readonly flags) via src/services/agent-bridge.ts:
| Harness | Native format | Apply notes |
|---|---|---|
| codex | .codex/agents/*.toml | developer_instructions, model_reasoning_effort, sandbox_mode |
| claude-code | .claude/agents/*.md + YAML | Richest metadata; extra Claude-only keys preserved in metadata.extra |
| cursor | .cursor/agents/*.md + YAML | readonly / is_background; sandbox_mode: read-only maps to readonly: true |
| opencode, github-copilot, copilot-cli, grok-build | */agents/*.md | Markdown with optional frontmatter |
generic harnesses with agents: paths | *.md | Same as OpenCode/Copilot emission |
Plugin import scans agents/*.md and agents/*.toml (Codex packs). Cross-harness apply re-emits valid native files per target harness.
Harness reference
Legend for the Resources column: instr instructions · skill skills · rule rules · mcp MCP · perm permissions · hook hooks · agent agents · cmd commands · env env vars · model model config.
| ID | Name | Serializer | Resources | Skill emission | Plugin install |
|---|---|---|---|---|---|
claude-code | Claude Code | Native | instr, skill, rule, mcp, perm, hook, agent, cmd, env, model | Native skills | Yes |
codex | Codex | Native | instr, skill, rule, mcp, perm, hook, agent, env, model | Native skills | — |
cursor | Cursor | Native | instr, skill, rule, mcp, hook, agent | Native skills | Yes |
opencode | OpenCode | Native | instr, skill, mcp, agent, cmd | Native skills | — |
github-copilot | GitHub Copilot | Native | instr, skill, mcp, agent | Instruction-only | — |
copilot-cli | Copilot CLI | Native | instr, skill, mcp, agent | Native skills | — |
gemini-cli | Gemini CLI | Native | instr, skill, cmd | Instruction-only | — |
antigravity | Antigravity | Generic | instr, skill, rule, mcp, cmd | Native skills | — |
amazon-q | Amazon Q Developer | Generic | instr, rule, mcp | — | — |
windsurf | Windsurf | Generic | instr, skill, rule, mcp | Instruction-only | — |
cline | Cline | Generic | instr, skill, rule, mcp | Instruction-only | — |
roo | Roo Code | Generic | instr, skill, rule, mcp | Native skills | — |
continue | Continue | Generic | instr, skill, mcp | Native skills | — |
goose | Goose | Native | instr, skill, mcp, hook, cmd | Native skills | Yes |
trae | Trae | Generic | instr, skill, rule, mcp | Native skills | — |
openhands | OpenHands | Generic | instr, skill, mcp | Native skills | — |
kiro | Kiro | Generic | instr, skill, rule | Instruction-only | — |
warp | Warp | Generic | instr, skill | Native skills | — |
pi | Pi | Generic | instr, skill | Native skills | — |
aider | Aider | Generic | instr | — | — |
zed | Zed | Generic | instr, skill | Native skills | — |
devin | Devin | Generic | instr, skill | Native skills | — |
jules | Jules | Generic | instr, skill | Native skills | — |
cody | Sourcegraph Cody | Generic | instr, mcp | — | — |
grok-build | Grok Build | Native | instr, skill, mcp, perm, hook, agent, cmd, model | Native skills | — |
deepseek-harness | DeepSeek Harness | Native | instr, skill, mcp, perm, hook, agent, model | Native skills | Yes |
muse-code | Muse Code | Native | instr, skill, mcp, hook | Native skills | — |
amp | Amp | Generic | instr, skill | Native skills | — |
kilo | Kilo Code | Generic | instr, skill | Native skills | — |
augment | Augment | Generic | instr, skill | Native skills | — |
firebender | Firebender | Generic | instr, skill | Native skills | — |
junie | Junie | Generic | instr, skill | Native skills | — |
zencoder | Zencoder | Generic | instr, skill | Native skills | — |
deepagents | Deep Agents | Generic | instr, skill | Native skills | — |
qwen-code | Qwen Code | Generic | instr, skill | Native skills | — |
crush | Crush | Generic | instr, skill | Native skills | — |
droid | Droid | Generic | instr, skill | Native skills | — |
codebuddy | CodeBuddy | Generic | instr, skill | Native skills | — |
mux | Mux | Generic | instr, skill | Native skills | — |
kode | Kode | Generic | instr, skill | Native skills | — |
command-code | Command Code | Generic | instr, skill | Native skills | — |
cortex | Cortex Code | Generic | instr, skill | Native skills | — |
neovate | Neovate | Generic | instr, skill | Native skills | — |
On-disk paths (selected harnesses)
These are the primary project paths HarnessTap scans and writes. Global paths follow the same keys under each harness home directory (see ht harness list --format json).
| Harness | Instructions | Skills | Rules | MCP | Agents | Commands | Settings |
|---|---|---|---|---|---|---|---|
| claude-code | CLAUDE.md | .claude/skills/ | .claude/rules/ | .mcp.json | .claude/agents/ | .claude/commands/ | .claude/settings.json |
| codex | AGENTS.md | .agents/skills/ | — | .codex/config.toml | .codex/agents/ | — | .codex/config.toml |
| cursor | AGENTS.md (+ legacy .cursorrules) | .agents/skills/ | .cursor/rules/ | .cursor/mcp.json | .cursor/agents/ | — | — |
| opencode | AGENTS.md | .opencode/skills/ | — | opencode.json | .opencode/agents/ | .opencode/commands/ | — |
| github-copilot | .github/copilot-instructions.md | .agents/skills/ | — | (global ~/.copilot/mcp-config.json) | .github/agents/ | — | — |
| copilot-cli | AGENTS.md | .agents/skills/ | — | .copilot/mcp-config.json | .github/agents/ | — | — |
| gemini-cli | AGENTS.md | .agents/skills/ | — | — | — | commands/ | gemini-extension.json |
| antigravity | AGENTS.md (+ GEMINI.md) | .agents/skills/ | .agents/rules/ | .agents/mcp_config.json | — | .agents/workflows/ | — |
| amazon-q | AmazonQ.md (+ AGENTS.md) | — | .amazonq/rules/ | .amazonq/mcp.json | — | — | — |
| windsurf | .windsurfrules | .agents/skills/ | .windsurf/rules/ | (global MCP config) | — | — | — |
| roo | AGENTS.md | .roo/skills/ | .roomodes | .roo/mcp.json | — | — | — |
| goose | AGENTS.md, .goosehints | .agents/skills/ (+ .goose/skills/) | — | .config/goose/config.yaml (project), ~/.config/goose/config.yaml (global) | — | recipes/*.yaml | ~/.config/goose/config.yaml |
| aider | CONVENTIONS.md (+ AGENTS.md) | — | — | — | — | — | .aider.conf.yml |
| zed | AGENTS.md (+ .rules) | .agents/skills/ | — | — | — | — | — |
| devin | AGENTS.md (+ AGENTS.local.md) | .agents/skills/ | — | — | — | — | .devin/config.json |
| grok-build | AGENTS.md (+ AGENT.md) | .grok/skills/ | — | .grok/config.toml | .grok/agents/ | .agents/commands/ | .grok/config.toml |
| deepseek-harness | AGENTS.md (+ CLAUDE.md) | .dsh/skills/ | — | ~/.dsh/cordis.patch.yml (global) | ~/.dsh/.agent-presets/ | — | ~/.dsh/settings.yaml |
| muse-code | AGENTS.md (also reads CLAUDE.md, .agents/AGENTS.md, .claude/CLAUDE.md) | .agents/skills/ | — | ~/.config/muse/settings.json (mcp_servers, global only) | — | — | ~/.config/muse/settings.json |
| cody | AGENTS.md | — | — | (global ~/.config/sourcegraph/cody.json) | — | — | cody.json |
Cursor global user skills live under ~/.cursor/skills/. Cursor also maintains app-managed built-ins under ~/.cursor/skills-cursor/ — HarnessTap inventories those on profile status / apply-preview (host_managed.cursor) but never imports or applies them.
Copilot CLI home state lives under ~/.copilot/. Detection uses ~/.copilot/settings.json and ~/.copilot/installed-plugins/ in addition to ~/.copilot/skills/ and ~/.copilot/mcp-config.json. Installed plugins are imported as pins from ~/.copilot/installed-plugins/<marketplace>/<plugin>/.
Generic harnesses in the skills-only tier use harness-specific skill roots such as .kilocode/skills/, .crush/skills/, or .factory/skills/ with AGENTS.md instructions — see the registry for the full list.
Goose context engineering
HarnessTap maps Goose context engineering surfaces as follows:
| Goose feature | HarnessTap support |
|---|---|
goosehints (.goosehints, nested, global ~/.config/goose/.goosehints) | Scanned and emitted as instruction resources |
Agent skills (.agents/skills/, legacy .goose/skills/) | Native skill resources |
Open Plugins (plugin.json, .goose-plugin/, .agents/plugins/) | Plugin-source import + goose plugin install sync |
Hooks (plugin hooks/hooks.json) | hook resources; apply emits .agents/plugins/harnesstap-plugin/ |
MCP extensions (config.yaml extensions:) | mcp_server resources via native serializer |
Recipes (recipes/*.yaml) | command resources |
| Subagents, plan mode, prompt templates, MOIM, memory extension | Runtime-only — not plugin resources (see portability limits) |
Antigravity notes
Antigravity IDE, Antigravity CLI (agy), and AGY share the same workspace layout under .agents/. Workflows (.agents/workflows/*.md) map to HarnessTap commands. Global config lives under ~/.gemini/ (GEMINI.md, config/mcp_config.json, skills/, config/global_workflows/). This is distinct from the thinner gemini-cli entry.
Grok Build notes
Grok Build’s native layout under .grok/ maps as follows:
| Grok surface | HarnessTap support |
|---|---|
AGENTS.md (AGENT.md, Agents.md) | instruction resources |
Skills (.grok/skills/, ~/.grok/skills/, also ~/.agents/skills/) | Native skill resources |
Agents (.grok/agents/*.md) | agent resources |
Hooks (.grok/hooks/*.json) | hook resources; apply emits .grok/hooks/harnesstap.json |
MCP ([mcp_servers] in .grok/config.toml) | mcp_server resources |
Permissions ([permission] allow/deny/ask or rules) | permission resources |
Commands (.agents/commands/, ~/.agents/commands/) | command resources (skills also appear as slash commands at runtime) |
Default model ([models] default in ~/.grok/config.toml) | model_config on global apply only — project .grok/config.toml cannot carry [models] |
| Personas / roles / plugins / sandbox.toml | Runtime/config-only — not plugin resources today |
DeepSeek Harness notes
DeepSeek Harness is a developer preview; the Cordis patch schema can change. Home files live under $DSH_HOME if set, otherwise ~/.dsh. Detection uses distinctive .dsh/skills/ or .dsh/hooks/ — not AGENTS.md alone.
| DeepSeek surface | HarnessTap support |
|---|---|
AGENTS.md (CLAUDE.md) | instruction resources |
Skills (.dsh/skills/) | Native skill resources |
MCP ($DSH_HOME/cordis.patch.yml home patch) | Live MCP is global only — not project |
Hooks ($DSH_HOME/cordis.patch.yml configPath) | Live hooks are $DSH_HOME/hooks/harnesstap.json (Claude command subset via @deepseek-ai/dsh-hooks-claude-code); project .dsh/hooks/ is scanned and written but not wired into Cordis |
Agent presets ($DSH_HOME/.agent-presets/) | Persona-only user presets — not a copy of shipped standard |
| Permissions | Named presets workspace-write and danger-full-access only |
| Plugin install | dsh plugin --profile web add ($DSH_HOME/profiles/web/) — web profile only |
Muse Code notes
Muse Code (Meta) user settings live at ~/.config/muse/settings.json. The file must include "schema_version": 1 whenever it exists. HarnessTap merges mcp_servers and user hooks into that file and leaves model defaults, TUI, runtime_capabilities, telemetry, and managed_hooks_path alone. MCP is user-settings only — there is no documented project MCP path.
Detection uses distinctive .muse/hooks.json and/or ~/.config/muse/ (settings.json or the config directory). Shared AGENTS.md / .agents/skills/ alone do not count as Muse. muse init only writes AGENTS.md; a Muse-only machine is still detected from the home config directory.
| Muse surface | HarnessTap support |
|---|---|
AGENTS.md (load walk: AGENTS.md, CLAUDE.md, .agents/AGENTS.md, .claude/CLAUDE.md) | instruction resources; apply emits AGENTS.md |
Skills (<repo>/.agents/skills/, also discovers .claude/skills and .codex/skills) | Native skill resources; apply writes .agents/skills/ only (no double-emit to Claude/Codex trees) |
Project hooks (<project>/.muse/hooks.json) | hook resources |
User hooks (hooks in ~/.config/muse/settings.json) | Merged into user settings |
MCP (mcp_servers in user settings; stdio / streamable_http) | mcp_server resources on global apply only |
Memory (.agents/memory/) | Skipped — not emitted day one |
| Workflows / observer agents | Runtime-only — out of scope |
Related commands
ht harness list # all registered harnesses
ht harness list --supported # native serializers only
ht harness status # global main + alias selection
ht harness project status --project . # per-project harness prefs + cursor_skill_mode
ht scan . --dry-run # detect harnesses and resources in a repo
ht environment list # named environments (env vars, models, permissions)See also
- Portability limits — fidelity matrix and workarounds
- CLI command reference — full command surface