store

store is a skill for Claude Code, Codex from rkumar70900/store-mcp. It costs 46 tokens per session (3,059 once invoked), scanned A, original, MIT.

Instructions for using a shared store that holds personal lists such as todos, bookmarks, reading, and watching, plus project and initiative records. The guide explains how to inspect each list before changing it.

In plain words
What is it for?
Use it to read, add, update, or softly remove records from the store's collections.
Why use it?
It prevents failed or incorrect updates by requiring the exact fields and allowed values to be checked instead of guessed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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.

agentmods
npx agentmods add skills/rkumar70900/store-mcp/store
Any agent
npx skills add rkumar70900/store-mcp --skill store
Clone the repo
git clone --depth 1 https://github.com/rkumar70900/store-mcp

Made for: Claude Code, Codex.

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 store

README.md
[![agentmods](https://agentmods.dev/badge/skills/rkumar70900/store-mcp/store.svg)](https://agentmods.dev/skills/rkumar70900/store-mcp/store)
Your own site
<a href="https://agentmods.dev/skills/rkumar70900/store-mcp/store"><img src="https://agentmods.dev/badge/skills/rkumar70900/store-mcp/store.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,059 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.03059
Opus 5 $0.00023 $0.01529
Sonnet 5 $0.00009 $0.00612
Haiku 4.5 $0.00005 $0.00306

Measured 6d ago against content hash 759bc585944c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

store 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 6d 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.

store/skills/store/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using the store

store is one server holding several collections — separate lists, each with its own fields. The collections are todos, things, bookmarks, reading, and watch, plus — for tracking my work across projects — projects and initiatives. More can be added without changing these tools.

There are six tools, and they never change no matter how many collections exist:

Tool Use it to
store_guide() Read this guide. Call it first, before anything else.
store_describe(collection) See a collection's exact fields, types, and allowed values.
store_add(collection, data) Add one record. data is an object of field → value.
store_update(collection, id, patch) Change fields on an existing record.
store_remove(collection, id) Delete a record (soft — recoverable).
store_query(collection, search, all, limit) Read records.

The one rule that matters most

Do not guess field names. Each collection has a fixed set of fields. If you are unsure what a collection accepts, call store_describe(collection) — it is cheaper than a failed write. Sending a field that doesn't exist (e.g. a made-up priority or urgent) will be rejected; when that happens, read the error, it names the valid fields, and retry once with a correct field. Do not loop.

Don't smuggle an unsupported concept into another field. If the user asks for something a collection simply doesn't model — a todo's priority, importance, or urgency — do NOT write the word into notes (or any other field) to fake it. That silently corrupts the data. Instead tell the user plainly that this list doesn't track that. A todo has no priority concept; its only states are open and done.

Which collection?

Every request maps to one collection. Route by what the user wants to do:

  • Something small to get done, remember, or act on → todos.
  • A physical object and where it's stored → things.
  • A link or item to read / watch / keep → the distractor triple below.
  • A larger thread of work on a project — building a feature, writing an article, a research effort, a hardware build — or when I ask what I'm working on, my backlog, priorities, or focusinitiatives (with projects as the list of projects they belong to). The line vs todos: a todo is one small task; an initiative is a bigger body of work with its own lifecycle and a home project. "Call the dentist" is a todo; "Add offline mode to the mobile app" is an initiative.

Read the full file on GitHub · 218 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.

  1. 6d ago First seen · 218 lines · 46 tokens per session scan A 759bc585944c

Subscribe to this mod's changes

store is a skill published in the GitHub repository rkumar70900/store-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 3,059 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

things-mac

Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Otto to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

elizaOS/eliza · 67 tokens

gsd-ns-manage

Route to the appropriate management skill based on the user's intent. gsd-config (settings + advanced + integrations + profile) and gsd-workspace (new + list + remove) are post-#2790 consolidated entries.

open-gsd/gsd-core · 16 tokens

slack-tools

Slack workspace management and automation specialist.

RightNow-AI/openfang · 10 tokens

triage-inbox

Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action…

pedrohcgs/claude-code-my-workflow · 132 tokens

ceo-setup

One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 60 tokens

service-desk

Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…

cbrock84/headcount · 73 tokens