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/rkumar70900/store-mcp/storenpx skills add rkumar70900/store-mcp --skill storegit clone --depth 1 https://github.com/rkumar70900/store-mcpWrote 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/rkumar70900/store-mcp/store)<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>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 | $0.00046 | $0.03059 |
| Opus 5 | $0.00023 | $0.01529 |
| Sonnet 5 | $0.00009 | $0.00612 |
| Haiku 4.5 | $0.00005 | $0.00306 |
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.
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 focus → initiatives (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.
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.
- 6d ago First seen · 218 lines · 46 tokens per session scan A 759bc585944c
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.
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.
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.
slack-tools
Slack workspace management and automation specialist.
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…
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.
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…