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 agentmods add skills/onurpolat05/alba/create-skillnpx skills add onurpolat05/ALBA --skill create-skillgit clone --depth 1 https://github.com/onurpolat05/ALBAWrote 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/onurpolat05/alba/create-skill)<a href="https://agentmods.dev/skills/onurpolat05/alba/create-skill"><img src="https://agentmods.dev/badge/skills/onurpolat05/alba/create-skill.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 | $0.00112 | $0.01107 |
| Opus 5 | $0.00056 | $0.00553 |
| Sonnet 5 | $0.00022 | $0.00221 |
| Haiku 4.5 | $0.00011 | $0.00111 |
Grade A, and why
create-skill 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ALBA Skill Creator
Interactively create a new skill with proper frontmatter and structure.
Process
Step 1: Understand the Skill
Ask these questions (one at a time):
- "What should this skill do?" - Core purpose in one sentence
- "What exact phrases should trigger it?" - Push for the words the user actually types, not abstract categories. "research", "look into X", "find info on" beats "information gathering".
- "When should it NOT fire?" - The nearest existing skill it could be confused with. This
answer becomes the
Do NOT use for ...clause and is what stops two skills fighting over the same prompt. - "What inputs does it need?" - What the user provides
- "What output should it produce?" - Format, structure
- "Does it need web access or just local files?" - Determines tools and context
Step 2: Determine Configuration
Based on answers, decide:
Context:
inline- Quick operations that need conversation context (< 1 min), or anything that asks the user a questionfork- Heavy operations that should run as a subagent (research, log analysis, wide file sweeps). A fork keeps its own reading out of the main context window.
If you choose fork, you must also decide background. Forked skills default to
background: true — they detach and report back later. Set background: false when the user is
waiting for the answer in the same turn, which is the normal case for an interactive skill. Leave
the default only for genuinely fire-and-forget work. (background needs Claude Code v2.1.218+.)
Tools: Pick from:
- Read, Write, Edit, Glob, Grep (file operations)
- WebSearch, WebFetch (web access)
- Bash (system commands)
- AskUserQuestion (user interaction - only works with
inline; a fork has no one to ask)
Optional fields worth considering: argument-hint if the skill takes arguments,
disable-model-invocation: true if firing it by accident would damage something,
model if the work is mechanical enough to run on a cheaper model. Full reference with every
valid field: templates/skills/SKILL-TEMPLATE.md.
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 First seen · 120 lines · 112 tokens per session scan A 9c31190be42f
create-skill is a skill published in the GitHub repository onurpolat05/ALBA (20 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 1,107 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 skills, from other repositories
vibe-research
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me start a new project".
kn-research
Use when you need to understand existing code, find patterns, search project knowledge, investigate current external facts, or explore a large codebase before implementation.
kn-init
Use at the start of a new session to read project docs, understand context, and see current state.
trellis-brainstorm
Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex…
trellis-session-insight
Reach into past AI conversation history through the trellis mem CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work…
trellis-channel
Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.