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 aegntic/cldcde --skill ae-ltd-skill-buildergit clone --depth 1 https://github.com/aegntic/cldcdeWrote 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/aegntic/cldcde/ae-ltd-skill-builder)<a href="https://agentmods.dev/skills/aegntic/cldcde/ae-ltd-skill-builder"><img src="https://agentmods.dev/badge/skills/aegntic/cldcde/ae-ltd-skill-builder/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/aegntic/cldcde/ae-ltd-skill-builder"><img src="https://agentmods.dev/badge/skills/aegntic/cldcde/ae-ltd-skill-builder.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 | $0.00048 | $0.00933 |
| Opus 5.5 | $0.00019 | $0.00373 |
| Sonnet 5.5 | $0.00010 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
ae-ltd-skill-builder 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 today.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AE.LTD Skill Builder
What This Skill Does
Production-ready skill factory for Claude Code. Creates skills that Claude can autonomously discover and use across all surfaces (Claude.ai, Claude Code, SDK, API).
- Scaffold new skills with proper structure
- Validate and fix existing skills
- Generate templates (basic, intermediate, advanced)
- Automate lifecycle with hooks
Prerequisites
- Claude Code 2.0+ or Claude.ai with Skills support
- Basic understanding of Markdown and YAML
- Text editor or IDE
Quick Start
# Interactive skill creation
./scripts/create-skill.sh my-new-skill
# Validate all skills
./scripts/validate-skill.sh
# Auto-fix naming issues
./scripts/fix-skill.sh
Included Tooling
Scripts (scripts/)
| Script | Purpose |
|---|---|
create-skill.sh |
Interactive skill scaffolding |
validate-skill.sh |
Validate structure & frontmatter |
fix-skill.sh |
Auto-fix naming and frontmatter issues |
lint-skill.sh |
Check content quality |
test-skill.sh |
Test skill integration |
Hooks (hooks/)
| Hook | When |
|---|---|
pre-task.sh |
Before skill execution |
post-task.sh |
After skill completes |
pre-edit.sh |
Before file modification |
post-edit.sh |
After file modification |
session-end.sh |
Session cleanup |
Prompts (prompts/)
| File | Purpose |
|---|---|
system.md |
System context extensions |
examples.md |
Example interactions |
Templates (resources/templates/)
basic/SKILL.md.template- Minimal structureintermediate/SKILL.md.template- Standard sectionsadvanced/SKILL.md.template- Full-featured
Documentation (docs/)
ADVANCED.md- Advanced patterns, MCP integrationTROUBLESHOOTING.md- Common issues & solutionsHOOKS.md- Complete hooks referencePROMPTS.md- Prompts system guide
Workflow
- Create Skill
./scripts/create-skill.sh my-skill --intermediate
What ships with it
26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 236 B
- docs/ADVANCED.md 7.2 KB
- docs/HOOKS.md 4.7 KB
- docs/PROMPTS.md 4.5 KB
- docs/TROUBLESHOOTING.md 6.0 KB
- hooks/post-edit.sh 1.8 KB runs code
- hooks/post-task.sh 1.4 KB runs code
- hooks/pre-edit.sh 1.5 KB runs code
- hooks/pre-task.sh 1.1 KB runs code
- hooks/session-end.sh 1.9 KB runs code
- prompts/examples.md 2.9 KB
- prompts/system.md 1.7 KB
- resources/examples/ae-ltd-skill-builder-demo/hooks/post-task.sh 114 B runs code
- resources/examples/ae-ltd-skill-builder-demo/hooks/pre-task.sh 112 B runs code
- resources/examples/ae-ltd-skill-builder-demo/scripts/example.sh 536 B runs code
- resources/examples/ae-ltd-skill-builder-demo/SKILL.md 1.4 KB
- resources/schemas/skill.schema.json 814 B
- resources/templates/advanced/SKILL.md.template 2.9 KB
- resources/templates/basic/SKILL.md.template 419 B
- resources/templates/intermediate/SKILL.md.template 1.0 KB
- scripts/create-skill.sh 9.8 KB runs code
- scripts/fix-skill.sh 4.9 KB runs code
- scripts/lint-skill.sh 9.6 KB runs code
- scripts/test-skill.sh 4.4 KB runs code
- scripts/validate-skill.sh 8.9 KB runs code
- SKILL.toml 538 B
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.
- today First seen · 145 lines · 48 tokens per session scan A e150c23e8fe4
ae-ltd-skill-builder is a skill published in the GitHub repository aegntic/cldcde (11 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 933 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 2026-11-05.
Other skills, from other repositories
hono-core
Hono ultrafast web framework fundamentals - routing, context, handlers, and response patterns for multi-runtime deployment.
tauri-django-react
Agents should invoke this skill for Tauri + Django + React desktop apps, especially backend lifecycle, CORS/auth, frontend integration, mandatory light/dark theming, German/English i18n, build packaging, dual desktop/web deployment, Rust commands, and platform-specific gotchas.
rewrite-in-rust
Assess, plan, execute, and verify migrations of existing software to Rust. Use for requests to rewrite, port, migrate, or oxidize a codebase, library, module, application, or subsystem in Rust, including RIIR requests. Adapts to the source language and repository; supports incremental replacement, a separate complete…
project-readme
Use when creating, updating, reviewing, restructuring, or harmonizing a repository's project README from verified local evidence for user-oriented or developer/library-oriented readers, with separately approved TECHNICAL.md and DEVELOPMENT.md companions when needed.
requirements-engineering
Elicits, documents, checks, and agrees on requirements with users and stakeholders. Separates problem, requirement, and solution, and keeps evidence, agreement, and approval apart. Use this skill for requirements, specifications, user stories, feature requests, stakeholder interviews, workshops, surveys, requirements…
repo-explorer
Agents should invoke this skill before modifying unfamiliar codebases, answering where/how something is implemented, tracing dependencies, mapping repo structure, or planning changes. Explores a repository and returns a strict JSON handoff with key files, symbols, risks, and evidence.