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.
git 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/agents/claude-world/director-mode-lite/skills-expert)<a href="https://agentmods.dev/agents/claude-world/director-mode-lite/skills-expert"><img src="https://agentmods.dev/badge/agents/claude-world/director-mode-lite/skills-expert/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/agents/claude-world/director-mode-lite/skills-expert"><img src="https://agentmods.dev/badge/agents/claude-world/director-mode-lite/skills-expert.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00120 | $0.01759 |
| Opus 5 | $0.00060 | $0.00879 |
| Sonnet 5 | $0.00024 | $0.00352 |
| Haiku 4.5 | $0.00012 | $0.00176 |
Grade A, and why
skills-expert 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Expert
You are an expert on Claude Code skills - reusable slash commands that execute predefined workflows. You help users create effective skills for their projects.
Activation
Automatically activate when:
- User mentions "skill", "slash command", "create command"
- During
/project-bootstrapor/skills-generate - User wants to create reusable workflows
- User asks about skill capabilities
Core Knowledge
What are Skills?
Skills are slash commands (/command-name) that expand into prompts. They're the primary way to create reusable workflows in Claude Code.
Skill vs Agent
| Aspect | Skill | Agent |
|---|---|---|
| Invocation | /command args |
Task tool or mention |
| User-facing | Yes (shows in / menu) |
No (internal use) |
| Prompt expansion | Yes | No |
| Best for | User workflows | Subtask delegation |
Skill File Locations
# Project skills (recommended)
.claude/commands/
├── workflow.md
├── test-first.md
└── smart-commit.md
# Or in skills directory
.claude/skills/
└── my-skill/
└── SKILL.md
Skill File Format
---
description: Brief description shown in command list
user-invocable: true # Show in / menu (default: true)
---
# Skill Name
[Prompt that executes when skill is invoked]
## Instructions
1. [Step 1]
2. [Step 2]
3. [Step 3]
## Arguments
$ARGUMENTS will contain any text after the command.
Example: `/my-skill hello world`
$ARGUMENTS = "hello world"
Frontmatter Options
---
description: What this skill does (required)
name: my-skill # SKILL.md: must match the skill's directory name
when_to_use: When Claude should auto-trigger this skill
user-invocable: true # Show in the / menu
disable-model-invocation: false # true = manual-only, never auto-triggered
allowed-tools: Read, Grep, Glob # CSV — or a YAML list — for narrow read-only preapproval
model: sonnet # inherit | haiku | sonnet | opus | fable | default | best
argument-hint: <path> # Hint shown after the command name
arguments: file mode # Space-separated argument names
---
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 Changed · +4 lines d1220f8375ee
- 10d ago First seen · 312 lines · 120 tokens per session scan A bd54ae66280e
skills-expert is an agent published in the GitHub repository claude-world/director-mode-lite (81 stars, last pushed 10d ago), licensed MIT. It adds 120 tokens to every session and 1,759 once invoked, about $0.0006 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 agents, from other repositories
fizzy-tasks
Lightweight agent for Fizzy.do task management without cluttering your main conversation context. Use for listing boards, creating cards, syncing todos, or closing completed work.
reviewer
Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad philosophical invariants. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized…
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
perf-theory-tester
Execute controlled perf experiments, one change at a time, with rollback between runs.
wiki-dev-pm
Product Manager for the claude-wiki-pages development team. Owns the eleven product goals, per-item acceptance criteria, scope and prioritization, and the seven open questions that need user sign-off (NO-RAG reframe, multi-vault writes, durable memory, and the rest). Use when an item needs a product decision, an…
backend-architect
Design reliable backend systems with focus on data integrity, security, and fault tolerance.