FAQ
director-mode-lite is a Claude Code plugin with 36 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes changelog-observer, agent-check, agent-template. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
> /plugin marketplace add claude-world/director-mode-lite> /plugin install director-mode-lite@director-mode-lite
Repo: claude-world/director-mode-lite
Director Mode Lite is a guidance-first development toolkit. It gives three agentic CLIs a shared operating brief, reusable skills, adapted agents, and a portable way to hand unfinished work to one another.
It adds no permission gates, deny rules, or forced workflow. Claude Code, Codex, and Grok keep their native controls, so users can choose their preferred trusted/full-access mode without Director Mode getting in the way.
git clone https://github.com/claude-world/director-mode-lite.git
cd director-mode-lite
./install.sh --cli all /path/to/your-project
Then open the project with any supported CLI:
claude
codex
grok
For the product's full-capability, no-prompt profile, use the installed launcher in a trusted workspace:
.director-mode/bin/director-open claude
.director-mode/bin/director-open codex
.director-mode/bin/director-open grok
It uses each CLI's native open flagsβClaude bypassPermissions, Codex
danger-full-access with approvals disabled, and Grok always-approve with
its sandbox off. It does not emulate permissions with hooks. Native managed
policy can still override the flags, and existing global hooks can still run.
Start with the director-mode skill. When another CLI should continue, use
session-relay.
| Capability | Canonical source | Claude Code | Codex CLI | Grok Build |
|---|---|---|---|---|
| Repository guidance | portable/GUIDANCE.md | CLAUDE.md + .director-mode/ | AGENTS.md + .director-mode/ | reads both |
| Skills | skills/*/SKILL.md | .claude/skills/ | .agents/skills/ | reads Claude-compatible skills |
| Agents | agents/*.md | .claude/agents/*.md | generated .codex/agents/*.toml | generated .grok/agents/*.md |
| Optional context hook | hooks/advisory.sh | settings.local.json | .codex/hooks.json | none (passive stdout is ignored) |
| Session continuity | director-handoff/v2 | new native session | new native session | new native session |
| Open launcher | scripts/director-open.sh | native bypass mode | native full-access mode | native always-approve / sandbox off |
| Read-only diagnosis | scripts/director-doctor.py | runtime/assets/hooks | runtime/assets/hooks | runtime/assets/hooks |
Grok's Claude compatibility is reused for skills, so the installer does not
create a second, conflicting .grok/skills/ tree. Agents receive minimal
native adapters because Claude-specific model, tool, and memory frontmatter is
not portable across every Grok release.
Before substantial work, keep five things visible:
The full guide lives at .director-mode/GUIDANCE.md after installation. It is
short by design: permanent instruction files are most useful when they contain
only facts needed in every session; detailed procedures belong in skills.
Claude, Codex, and Grok each store their own native conversation history. A vendor session ID cannot generally resume in a different vendor's CLI.
Director Mode solves the portable part: it creates JSON and Markdown packets with the goal, current state, decisions, Git snapshot, verification, blockers, and next steps. The receiver starts a new native session and reads the packet.
.director-mode/bin/director-relay create \
--from claude \
--to codex \
--goal "Finish the authentication refresh" \
--summary "API behavior is implemented; UI wiring remains" \
--completed "Added refresh-token rotation" \
--decision "Kept cookies httpOnly to match the existing threat model" \
--next "Update the sign-in form" \
--verification "API unit tests pass"
The relay automatically captures only Git metadata and diff statistics; it
does not scan raw transcripts, file contents, or credentials, or serialize the
process environment. The packet still contains user-supplied text, paths, and
Git filenames. Review those before sharing it outside the workspace; add
--reviewed when you want that review recorded in the packet.
Protocol v2 adds multi-hop lineage (root_id, parent_id, hop, and route)
and still validates v1 packets. Chain a Claude β Codex β Grok handoff with:
.director-mode/bin/director-relay create --parent \
--from codex --to grok \
--goal "Finish the authentication refresh" \
--summary "Codex completed UI wiring; integration tests remain" \
--next "Run the browser integration suite"
# Print a copyable interactive command
.director-mode/bin/director-relay continue --to codex
# Launch only when that is what you want
.director-mode/bin/director-relay continue --to codex --run
# Use a one-shot receiving session
.director-mode/bin/director-relay continue --to grok --headless --run
Other relay commands:
.director-mode/bin/director-relay validate
.director-mode/bin/director-relay status --json
.director-mode/bin/director-relay show
.director-mode/bin/director-relay list
status compares the captured branch, HEAD, Git status, and diff statistics to
the live worktree without blocking continuation. When --run is selected, the
receiver starts in the caller's live project root; a packet's old workspace
path is never trusted as an execution directory.
For same-provider history, keep the provider's native resume flow: Claude Code
uses --continue / --resume, Codex uses resume / exec resume, and Grok
uses --continue / --resume. Cross-provider work always starts a new native
session with the portable packet.
Grok Build also provides grok import for Claude Code sessions. That is a
helpful ClaudeβGrok shortcut; the portable packet remains the three-way format.
The 14 Markdown agents are the source representation. During installation, Director Mode:
name, description, and
developer_instructions;This adapts the interface without claiming that tool names, models, or runtime permissions are identical across vendors.
The repository ships 35 skills, including 31 user-invocable workflows. The cross-CLI entry points are:
director-mode β create a concise brief and verification contract;session-relay β leave or receive portable task state;handoff-claude, handoff-codex, handoff-grok β target-specific guidance;interop-router β suggest a useful next CLI without auto-executing it.The established workflow, planning, testing, review, debugging, documentation, and project-health skills remain available. CLI-specific surfaces are described inside the relevant skill instead of being hidden behind a universal claim.
The default is none: session relay, skills, agents, and guidance need no
hook. Optional --hooks guide adds useful SessionStart context only for Claude
Code and Codex. Grok loads guidance through AGENTS.md; current Grok releases
ignore passive SessionStart stdout, so installing that adapter would add work
without adding context. The optional shared executable:
deny, block, or a permission decision;Hooks are independent of permission mode. In particular, Claude hooks may also surface in Grok through its compatibility layer. Audit existing user-level hooks before calling an environment zero-interference.
./install.sh --update --hooks none is also the migration path: it surgically
removes Director-owned registrations and unmodified hook assets while
preserving custom hooks and locally modified files. The zero-hook verifier
checks this state instead of assuming it.
Ownership matching is exact: product-local .director-mode/... commands are
matched by their full asset path, while generic legacy .claude/hooks/...
names are removed only when the ownership inventory proves Director installed
them. A pre-existing, unowned same-name hook is preserved; automation mode
warns about the conflict instead of claiming or overwriting it.
Project hooks may require native trust or approval in Codex and Grok. Review the generated config with the CLI's own hook inspection UI.
./install.sh [--update] [--wizard]
[--cli all|claude|codex|grok]
[--hooks guide|none|automation]
[target-directory]
Common choices:
# Recommended: all adapters; register no Director Mode hooks
./install.sh --cli all --hooks none /path/to/project
# Add non-blocking SessionStart context for Claude and Codex
./install.sh --cli all --hooks guide /path/to/project
# Refresh files and migrate to zero Director-owned hooks
./install.sh --update --cli all --hooks none /path/to/project
# Interactive setup
./install.sh --wizard /path/to/project
The installer backs up an existing .claude/ directory, preserves an existing
project guide, and updates only its marked guidance block. Existing Codex hook
JSON is merged rather than replaced. Updates merge shipped skill files while
preserving extra user files in the skill directories.
Always choose the hook mode explicitly during an update. --hooks none
removes Director-owned hook registrations and unmodified owned hook assets;
guide and automation install or refresh those opt-in surfaces. Hooks owned
by the project, user, or another plugin remain native CLI configuration.
Before writing managed files, the installer rejects symlinked destination components and final files with multiple hard links. It stops with an error instead of following a managed path to another location or inode.
Version 2 defaults to zero-hook guidance. The previous Claude-only Auto-Loop, changelog, validator, and evolving-loop hook files are not installed or registered unless you explicitly choose:
./install.sh --hooks automation /path/to/project
This legacy mode is separate from the portable three-CLI layer. Its Stop-hook continuation behavior is Claude-specific and is not presented as a universal control mechanism.
The repository retains a Claude Code marketplace manifest and adds a Codex
plugin manifest. The two core skills bundle their own shared guide, relay, and
read-only doctor, so director-mode and session-relay remain functional in a
plugin-only install. The shell installer adds the complete project-local
surface: generated agents, repository guidance, launchers, and optional hook
adapters.
./tests/run-tests.sh
./scripts/verify-install.sh /path/to/project
python3 scripts/director-relay.py --help
python3 scripts/director-doctor.py --cwd /path/to/project --json --no-probe
In the doctor report, runtime.source identifies the selected project,
user, or bundled plugin runtime. Hook discovery covers project and user
Claude/Codex configs plus every discovered Grok hooks/*.json surface.
Malformed or shape-invalid files appear under hooks.invalid_surfaces; they
are never treated as evidence of a healthy zero-hook state.
Doctor exit status only confirms that the read-only report was generated. A
clean runtime requires empty runtime.missing and runtime.issues; a clean
hook conclusion requires hooks.known_registrations == 0 and an empty
hooks.invalid_surfaces. Use verify-install.sh when a pass/fail gate is
required.
The regression suite covers installer modes, native adapters, advisory hook behavior, exact hook ownership, symlink/hardlink write protection, packet creation/validation, metadata-only Git capture, project/user/plugin diagnosis, invalid hook surfaces, update behavior, and uninstall preservation.
git pull
./install.sh --update --cli all --hooks none /path/to/project
The important behavior change is the default: legacy automation is now opt-in.
To retire an older Director hook setup while preserving unrelated custom hooks,
run the same install command with --update --hooks none (the default is
already none; spelling it out makes the migration intent explicit).
See MIGRATION.md and FAQ.md for details.
Director Mode Lite is a community project from Claude World. It is not an official Anthropic, OpenAI, or xAI product.
.claude/
.claude-plugin/
marketplace.json
plugin.json
skills/
changelog-observer/
SKILL.md
template.md
.codex-plugin/
plugin.json
.devcontainer/
devcontainer.json
.github/
CODEOWNERS
copilot-instructions.md
dependabot.yml
FUNDING.yml
ISSUE_TEMPLATE/
bug_report.md
bug_report.yml
config.yml
feature_request.md
feature_request.yml
question.md
question.yml
PULL_REQUEST_TEMPLATE.md
SECURITY.md
workflows/
collect-stats.yml
validate.yml
.gitignore
.self-evolving-loop/
generated-skills/
.gitkeep
history/
.gitkeep
hooks/
continue-loop.sh
log-event.sh
phase-tracker.sh
settings-hooks.json
reports/
.gitkeep
state/
.gitkeep
templates/
executor-template.md
fixer-template.md
validator-template.md
agents/
agents-expert.md
claude-md-expert.md
code-reviewer.md
completion-judge.md
debugger.md
doc-writer.md
evolving-orchestrator.md
experience-extractor.md
hooks-expert.md
mcp-expert.md
requirement-analyzer.md
skill-evolver.md
skill-synthesizer.md
skills-expert.md
CHANGELOG.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
demo.sh
docs/
assets/
auto-loop-demo.gif
CLAUDE-TEMPLATE.md
DEVELOPMENT-PATTERNS.md
DIRECTOR-MODE-CONCEPTS.md
EVOLVING-LOOP-ARCHITECTURE.md
FAQ.md
HOOKS-GUIDE.md
MIGRATION.md
ROADMAP.md
SELF-EVOLVING-LOOP.en.md
SELF-EVOLVING-LOOP.ja.md
SELF-EVOLVING-LOOP.md
SELF-EVOLVING-LOOP.zh-TW.md
TEST-REPORT.md
examples/
01-calculator/
CLAUDE.md
package.json
README.md
02-rest-api/
CLAUDE.md
package.json
README.md
03-cli-tool/
CLAUDE.md
package.json
README.md
04-library/
CLAUDE.md
package.json
README.md
README.md
hooks/
_lib-changelog.sh
advisory.sh
auto-loop-stop.sh
log-bash-event.sh
log-file-change.sh
pre-tool-validator.sh
settings-hooks.json
idor-probe-claude-world_director-mode-lite.txt
install.sh
LICENSE
portable/
GUIDANCE.md
handoff.schema.json
README.md
scripts/
director-doctor.py
director-hooks.py
director-open.sh
director-relay.py
install_safety.py
install-ownership.py
install-portable.py
validate-frontmatter.py
verify-install.sh
SECURITY.md
skills/
agent-check/
SKILL.md
agent-template/
SKILL.md
agents/
SKILL.md
auto-loop/
SKILL.md
changelog/
SKILL.md
check-environment/
SKILL.md
claude-md-check/
SKILL.md
claude-md-template/
SKILL.md
code-reviewer/
SKILL.md
debugger/
SKILL.md
director-mode/
agents/
openai.yaml
evals/
evals.json
references/
GUIDANCE.md
scripts/
director-doctor.py
SKILL.md
doc-writer/
SKILL.md
evolving-loop/
SKILL.md
evolving-status/
SKILL.md
focus-problem/
SKILL.md
getting-started/
SKILL.md
handoff-claude/
SKILL.md
handoff-codex/
SKILL.md
handoff-gemini/
SKILL.md
handoff-grok/
SKILL.md
hook-template/
SKILL.md
hooks-check/
SKILL.md
interop-router/
scripts/
check_cli_available.sh
score_decision.py
wrap_context.py
SKILL.md
mcp-check/
SKILL.md
plan/
SKILL.md
project-health-check/
SKILL.md
project-init/
SKILL.md
session-relay/
agents/
openai.yaml
evals/
evals.json
scripts/
director-relay.py
SKILL.md
skill-check/
SKILL.md
skill-template/
SKILL.md
skills/
SKILL.md
smart-commit/
SKILL.md
test-first/
SKILL.md
test-runner/
SKILL.md
workflow/
SKILL.md
tests/
run-tests.sh
test-doctor.sh
test-guidance-contract.sh
test-hooks.sh
test-install-wizard.sh
test-install.sh
test-plugin-only.sh
test-relay.sh
test-uninstall.sh
test-verify-install.sh
uninstall.sh
VERSIONΒ© 2026 Flowy Β· Free and open source
Built for Claude Code Β· Not affiliated with Anthropic