ALBA: Skill for Claude Code

.claude/skills/status/SKILL.md

status is a skill for Claude Code from onurpolat05/ALBA. It costs 95 tokens per session (538 once invoked), scanned A, original, MIT.

A read-only snapshot of current focus, task counts, recent activity, and blockers.

In plain words
What is it for?
Use it when you want to know what is active, what is finished, what is blocked, and when the last session occurred.
Why use it?
It gives a quick view of project status without changing tasks or other files.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is onurpolat05/ALBA's own configuration. It tells Claude Code how to work on ALBA itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ALBA configures →

Reuse

Borrowing it

Nothing to install: this file belongs to onurpolat05/ALBA. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/onurpolat05/ALBA/main/.claude/skills/status/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/onurpolat05/ALBA

Made for: Claude Code.

Wrote 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.

agentmods badge for status

README.md
[![agentmods](https://agentmods.dev/badge/skills/onurpolat05/alba/status.svg)](https://agentmods.dev/skills/onurpolat05/alba/status)
Your own site
<a href="https://agentmods.dev/skills/onurpolat05/alba/status"><img src="https://agentmods.dev/badge/skills/onurpolat05/alba/status.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 538 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00095 $0.00538
Opus 5 $0.00048 $0.00269
Sonnet 5 $0.00019 $0.00108
Haiku 4.5 $0.00010 $0.00054

Measured 7d ago against content hash 55d4c592a819, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

status 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 7d 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.

.claude/skills/status/SKILL.md · 54 lines

What it actually says

/status - Quick Status

Display current state in under 10 lines. No questions, pure read-only.

Steps

  1. Read memory/state/dashboard.md (silent)
  2. Read memory/state/todo.md (silent)
  3. Check memory/daily/ for last session date

Output Format

Status: YYYY-MM-DD

Focus: [Current top priority from dashboard]

Tasks: X active | Y completed
[If blockers exist: "Blocked: [blocker description]"]

Last session: YYYY-MM-DD

Rules

  • Maximum 8 lines of output
  • If dashboard doesn't exist: "No dashboard. Run /setup or create memory/state/dashboard.md"
  • If no daily logs exist: omit "Last session" line
  • Count active tasks: grep - [ ] in todo.md
  • Count completed: grep - [x] in todo.md
  • Extract blockers: look for "block", "wait", "stuck" keywords in dashboard
  • Don't load errors.md, learnings.md, or any .claude/docs/ files
  • This must be FAST - minimal file reads

Optional: pin a cheaper model

This skill reads two files, counts checkboxes and prints eight lines, and it is the skill people run most often — nothing here needs a frontier model. Adding a model: line to the frontmatter routes it to a smaller one and cuts the cost of every /status you ever run.

ALBA does not ship that pin, on purpose. A model id is a moving target: pin a dated one and you keep running last year's model long after a better and cheaper one exists, and you break outright if that id is ever retired. Check the model list for the current id, add the line yourself, and treat it as something you re-check — not as configuration that stays correct on its own.

Changes

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.

  1. 7d ago First seen · 54 lines · 95 tokens per session scan A 55d4c592a819

Subscribe to this mod's changes

status is a skill published in the GitHub repository onurpolat05/ALBA (20 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 538 once invoked, about $0.0005 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.

Related

Other skills, from other repositories