Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add claude-world/director-mode-lite/plugin install director-mode-liteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/claude-world/director-mode-lite/getting-started)<a href="https://agentmods.dev/skills/claude-world/director-mode-lite/getting-started"><img src="https://agentmods.dev/badge/skills/claude-world/director-mode-lite/getting-started.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.00518 |
| Opus 5 | $0.00018 | $0.00259 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
getting-started scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Getting started
Director Mode is a set of adaptable workflows, not a permission or policy layer. Keep the user's preferred CLI controls and choose only the skills useful for the current task.
1. Verify the portable surfaces
./scripts/verify-install.sh /path/to/project
A full three-CLI install currently provides 35 skills, 14 canonical Claude
agents, 14 Codex adapters, 14 Grok adapters, shared guidance, and the session
relay. Python 3 is required for installation and relay packets. jq is only a
legacy automation dependency; a normal zero-hook install does not need it.
Active hooks are optional. The default install deliberately registers none.
Use --hooks guide only when a short non-blocking Claude/Codex SessionStart
context is useful. Grok reads the same guidance from AGENTS.md without an
inert passive hook.
2. Choose a starting point
director-mode: define outcome, context, constraints, evidence, and the next decision for substantial work.workflow: use the full research → plan → implement → verify → review flow.focus-problem: understand an unfamiliar bug or codebase area.session-relay: leave portable state for Claude, Codex, or Grok to continue.smart-commit: review and prepare a conventional commit when requested.
Testing and TDD skills are available when they fit the repository or the user asks for them; they are not imposed on every task.
3. Let another CLI continue
.director-mode/bin/director-relay create \
--from claude --to codex \
--goal "Finish the current feature" \
--summary "Implementation is partly complete" \
--next "Inspect the worktree and continue"
.director-mode/bin/director-relay continue --to codex
The second command prints a copyable native command. It launches nothing until
the user explicitly adds --run.
Help
agents: list available agent roles.skills: browse the skill catalog.docs/FAQ.md: installation and relay questions.- https://claude-world.com: tutorials and updates.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 62 lines · 36 tokens per session scan A 49a68c54881b
getting-started is a skill published in the GitHub repository claude-world/director-mode-lite (81 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 518 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
concise
Concise communication mode. Cuts 60-70% of output tokens while keeping natural, readable English. Drops filler, hedging, and pleasantries but maintains grammar and sentence flow. Elaborate on request -- ask for detail and get it, then auto-return to concise. Use when user says "concise mode", "be concise", "less…
peekaboo
Provides runtime observation and interaction for native macOS interfaces through accessibility state and screenshots. Use when the task depends on visible or interactive state in a running SwiftUI/AppKit app: what is rendered, focused, selected, enabled, reachable through menus/windows/dialogs, or experienced across a…
mobile-flows-maestro
This skill should be used when Maestro is explicitly requested or already present and the task is to author, run, or debug iOS/Android Maestro flows; use Maestro MCP; or handle Maestro selectors, system UI, permissions, Keychain, JavaScript, waits, device state, flakiness, or CI. Evidence includes a .maestro directory…
validate-mobile
Run a Maestro flow on an explicitly selected iOS or Android device and report behavioral evidence.
validate-api
Run the project's Hurl scenarios with an OIDC access token passed as a secret variable.
kanso-audit
Use when the user asks for a code review, audit, pre-PR check, quality sweep, or pattern analysis of a diff, branch, module, or codebase. Also use when the user asks to "check" or "look over" their code for issues.