Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/claude-world/director-mode-litenpx agentmods add skills/claude-world/director-mode-lite/skill-checkWrote 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/skill-check)<a href="https://agentmods.dev/skills/claude-world/director-mode-lite/skill-check"><img src="https://agentmods.dev/badge/skills/claude-world/director-mode-lite/skill-check/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/skill-check"><img src="https://agentmods.dev/badge/skills/claude-world/director-mode-lite/skill-check.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 | $0.00035 | $0.01390 |
| Opus 5 | $0.00017 | $0.00695 |
| Sonnet 5 | $0.00007 | $0.00278 |
| Haiku 4.5 | $0.00003 | $0.00139 |
Grade A, and why
skill-check 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 5d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill File Validator
Validate skill files for correct format against the official Claude Code spec.
Validation Target
- With argument: validate specific file
- Without: validate all
.claude/skills/*/SKILL.md
Frontmatter Reference (official fields)
Skills support these fields. Only description is meaningfully required (a
skill with none of these still loads — name defaults to the directory name).
---
name: skill-name # Optional: defaults to directory name; lowercase, hyphenated
description: What it does # Recommended: shown in / menu and used for triggering
when_to_use: When to reach for it # Optional: appended to description for triggering
# (description + when_to_use truncated at 1,536 chars in listings)
user-invocable: true # Optional: default true; false hides from / menu (Skill tool still works)
model: sonnet # Optional: fable, opus, sonnet, haiku, inherit, default, best,
# sonnet[1m], opus[1m] (or a full model ID). NOT opusplan (session-only)
effort: medium # Optional: low, medium, high, xhigh, max
allowed-tools: # Optional: pre-approved tools. Accepts a comma-separated string
- Read # OR a YAML list — BOTH are official (list shown here as house style)
- Grep
- Glob
disallowed-tools: # Optional: explicitly blocked tools (string or YAML list)
- WebFetch
context: fork # Optional: run the skill in a subagent
agent: agent-name # Optional: subagent type when context: fork (default: general-purpose)
argument-hint: "[issue-number]" # Optional: autocomplete hint shown after the skill name
arguments: target flags # Optional: space-separated argument NAMES for $name substitution
# (e.g. arguments "target flags" -> use $target and $flags in the body).
# NOT a structured array of name/description/required objects.
disable-model-invocation: false # Optional: bool; true also blocks scheduled-task invocation
paths: # Optional: glob patterns that limit where the skill activates
- "src/**/*.ts"
shell: bash # Optional: bash or powershell for inline !`command` blocks
hooks: # Optional: skill-scoped lifecycle hooks (same schema as settings.json)
PreToolUse:
- matcher: Write
hooks:
- type: command
command: ./scripts/validate.sh
Stop:
- hooks:
- type: command
command: ./scripts/verify.sh
once: true
---
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.
- 5d ago Changed · +1 lines 32c448c33082
- 9d ago First seen · 140 lines · 35 tokens per session scan A 50bac6f73112
skill-check is a skill published in the GitHub repository claude-world/director-mode-lite (81 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 1,390 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.