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/extendnpx skills add onurpolat05/ALBA --skill extendgit 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/extend)<a href="https://agentmods.dev/skills/onurpolat05/alba/extend"><img src="https://agentmods.dev/badge/skills/onurpolat05/alba/extend.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 | $0.00132 | $0.01081 |
| Opus 5 | $0.00066 | $0.00541 |
| Sonnet 5 | $0.00026 | $0.00216 |
| Haiku 4.5 | $0.00013 | $0.00108 |
Grade A, and why
extend 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ALBA Extend
Add new capabilities to the agent system. Interactive and collaborative.
Step 1: Identify
Ask: "What would you like to add to your agent?"
Types:
- Skill - New capability (research, content creation, task automation...)
- Hook - Automated event response (session start, error logging...)
- Rule - Behavioral guideline (code standards, communication style...)
- Command - Custom /slash command
- MCP Integration - Connect external tool (Trello, Gmail, Calendar...)
Step 2: Build
Skills
- Understand: What task? What inputs/outputs? What tools?
- Check
templates/skills/for existing templates - Create
.claude/skills/[name]/SKILL.mdwith frontmatter:
The--- name: [skill-name] description: [what it does]. Use when user says "x", "y". Do NOT use for [z]. context: fork # fork = subagent (protects context), inline = main context background: false # fork only: wait for the result in this turn (fork defaults to background) allowed-tools: [tools] ---descriptionis the only field that decides whether the skill fires at the right moment — a bare one-line summary will not trigger reliably. Full field reference:templates/skills/SKILL-TEMPLATE.md. - Add to CLAUDE.md Skills table
- Test immediately
Hooks
- Identify the event. Common ones:
SessionStart,UserPromptSubmit,PreToolUse,PostToolUse,PostToolUseFailure,Stop,SubagentStop,PreCompact,PostCompact,SessionEnd. Claude Code v2.1.220 defines 30 events — seetemplates/hooks/README-hooks.mdfor the full list and each one's output contract. - Define what should happen when triggered
- Create
.claude/hooks/[name].shand make executable (chmod +x) - Add to
.claude/settings.json— note the nestedhooksarray; skipping the inner level is the most common reason a newly added hook never runs:{ "hooks": { "[EventType]": [ { "matcher": "Bash", "hooks": [ { "type": "command", "command": "${CLAUDE_PROJECT_DIR}/.claude/hooks/[name].sh", "timeout": 5 } ] } ] } }matcheronly applies to tool events. Use${CLAUDE_PROJECT_DIR}rather than a relative path, or the hook breaks for sessions started from a subdirectory. - Test by triggering the event
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 · 117 lines · 132 tokens per session scan A e52bc28ef4e6
extend is a skill published in the GitHub repository onurpolat05/ALBA (20 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 1,081 once invoked, about $0.0007 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.