Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add claude-world/director-mode-lite --skill workflowgit clone --depth 1 https://github.com/claude-world/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/workflow)<a href="https://agentmods.dev/skills/claude-world/director-mode-lite/workflow"><img src="https://agentmods.dev/badge/skills/claude-world/director-mode-lite/workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/claude-world/director-mode-lite/workflow"><img src="https://agentmods.dev/badge/skills/claude-world/director-mode-lite/workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.00990 |
| Opus 5.5 | $0.00021 | $0.00396 |
| Sonnet 5.5 | $0.00010 | $0.00198 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
workflow 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 1mo 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow
A structured approach to software development that emphasizes understanding, minimal implementation, testing, documentation, and clean commits.
Overview
Step 1: Focus Problem → Understand before coding
Step 2: Prevent Overdev → Only build what's needed (YAGNI)
Step 3: Test First → Red-Green-Refactor
Step 4: Document → Keep it clear and current
Step 5: Smart Commit → Conventional Commits
Step 1: Focus Problem (/focus-problem)
Goal: Thoroughly understand the problem before writing code.
Checklist
- What is the user need? (Who / What / Why)
- What defines success? (How to verify completion?)
- What are the boundaries? (What NOT to do?)
- What files/modules are affected?
- Is there existing similar functionality?
Use Explore Agent
(Use the active provider's native dispatcher; Claude pseudo-code is shown below.)
Before dispatch, preserve the bounded exploration request and expected result.
If Claude's Agent tool is unavailable or withheld, or Codex's spawn_agent
interface is unavailable or withheld, the maximum depth is reached, or a
concurrency limit rejects the call, do not retry or substitute assumptions.
Return an incomplete dispatch_request and do not advance the workflow.
Choose exactly one provider-native form:
- Claude Code:
Agent(subagent_type="Explore", model="haiku", prompt="<bounded prompt>") - Codex CLI:
spawn_agent(agent_type="explorer", task_name="workflow_explore", message="<bounded prompt>")
Agent(subagent_type="Explore", model="haiku", prompt="""
Explore the codebase for: [feature name] (thoroughness: medium)
Find related files, similar implementations, and test patterns.
""")
In Codex, send the same exploration request through spawn_agent(...); do not
invoke the Claude example as a second dispatch.
Step 2: Prevent Overdev
Goal: Ensure minimal viable implementation (YAGNI principle).
Red Flags
"We might need this later..." → Don't build it now
"Just in case..." → YAGNI
"Let's make it generic..." → Solve current problem only
"We should create a framework..." → Write concrete implementation
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.
- 1mo ago Changed · +15 lines f35b8a31313d
- 1mo ago First seen · 143 lines · 52 tokens per session scan A 0986d628d284
workflow is a skill published in the GitHub repository claude-world/director-mode-lite (80 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 990 once invoked, about $0.0002 per session on Opus 5.5. 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
quick
/quick — Lightweight Feature Workflow.
incremental-implementation
Use when implementing a multi-file change, building a feature from a breakdown, or writing a large amount of code. Not for a single settled ticket: use work.
ccc-testing
Testing domain router: picks the lane for TDD, E2E, visual regression, load testing, QA, regression checks, evals or verification and runs test-writing work in an isolated worktree. Use when the user asks to write tests, plan a test strategy, or test, verify or load-test a change.
wrap-up-branch
Finish a feature branch: add missing tests, review and fix the code, align docs, then merge only after explicit confirmation.
kanso-commit
Use when the user asks to commit changes, stage their work, write commit messages, or split the working tree into logical commits.
ctrl-c-v-tdd
Test-pattern doctrine. Tests are copyable from /.claude/patterns/tests/, three categories: input boundary, contract, effect. Make sure to consult this skill whenever code changes touch a boundary where someone else's code meets yours, even if the user doesn't say "test" or "TDD" — Claude tends to ship untested…