Instructions for managing tasks, goals and daily plans in Salta, an AI life planner. A task is one concrete action, while a goal is a larger outcome broken into phases and dated tasks.

Use it to review agendas and pending work, create tasks, create larger goals, divide goals into sections and add dated actions. It starts by checking the user's Salta context.

It helps turn vague intentions into organized work and keeps planning grounded in the user's priorities, schedule and existing tasks. It also prevents treating a multi-step goal as one unfinished task.

salta — Skill for Claude Code by jnuo

Install

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.

Any agent

npx skills add jnuo/salta-mcp --skill salta

Clone the repo

git clone --depth 1 https://github.com/jnuo/salta-mcp

Made for: Claude Code.

Or install salta, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jnuo/salta-mcp/salta/github.svg)](https://agentmods.dev/skills/jnuo/salta-mcp/salta)

Your own site

<a href="https://agentmods.dev/skills/jnuo/salta-mcp/salta"><img src="https://agentmods.dev/badge/skills/jnuo/salta-mcp/salta/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jnuo/salta-mcp/salta"><img src="https://agentmods.dev/badge/skills/jnuo/salta-mcp/salta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 686 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.00686
Opus 5	$0.00030	$0.00343
Sonnet 5	$0.00012	$0.00137
Haiku 4.5	$0.00006	$0.00069

Measured 9d ago against content hash 3a3a5a892096, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

salta 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 9d 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.

skills/salta/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working in Salta

Salta is the user's AI life planner — their whole day in one place: the chores they forget and the goals they keep putting off. You're connected to their real account over MCP. Every tool is plain CRUD (no Salta-side AI cost) — the judgment is yours. Use these tools to act; this skill is how to act well.

Start every session by grounding

Call get_context first. It returns who the user is, their North Star, priorities, and constraints. Plan around it — don't re-ask what Salta already knows. Then list_agenda (today/tomorrow) and list_tasks (pending) to see what's real before proposing anything.

Goal vs. task — the call that matters most

A task is one concrete action ("send the Q2 deck", "buy groceries"). Use create_task.
A goal is an outcome that takes many steps over time ("run a marathon", "learn Spanish"). Use create_goal, then break it into sections (phases) and add dated tasks to each.

When the user says something vague and aspirational ("I want to get fit", "I should learn to code"), that's a goal — create it and break it down. Do not drop a single bare task and call it done. Propose the breakdown, let them adjust, then create it.

The loop Salta runs on

Review → Plan → Execute, every day:

Review — list_agenda, list_tasks (catch overdue/carryover), get_context.
Plan — propose a focused, realistic day or week. Rank it. Fold carryover in.
Execute — create_task, complete_task, update_task (reschedule), and for goals create_goal + section tools. Use recurrence (rrule) for repeating routines instead of many one-offs.

Confirm before you create or change things — propose, don't surprise.

Remember things

When the user reveals a durable fact ("I work best early mornings", "no meetings on Fridays", "training for a half-marathon in October"), persist it with remember / update_context so future sessions plan around it. Use forget when something no longer holds. Don't make the user repeat themselves.

Read the full file on GitHub · 59 lines

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.

9d ago First seen · 59 lines · 59 tokens per session scan A 3a3a5a892096

Subscribe to this mod's changes

salta is a skill published in the GitHub repository jnuo/salta-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 686 once invoked, about $0.0003 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 2026-08-31.

Planning Productivity

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

salta