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 skills add matt-harding/allourthings-mcp --skill openclaw-skillgit clone --depth 1 https://github.com/matt-harding/allourthings-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/matt-harding/allourthings-mcp/openclaw-skill)<a href="https://agentmods.dev/skills/matt-harding/allourthings-mcp/openclaw-skill"><img src="https://agentmods.dev/badge/skills/matt-harding/allourthings-mcp/openclaw-skill/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.
<a href="https://agentmods.dev/skills/matt-harding/allourthings-mcp/openclaw-skill"><img src="https://agentmods.dev/badge/skills/matt-harding/allourthings-mcp/openclaw-skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00093 | $0.01182 |
| Opus 5.5 | $0.00037 | $0.00473 |
| Sonnet 5.5 | $0.00019 | $0.00236 |
| Haiku 4.5 | $0.00009 | $0.00118 |
Grade A, and why
allourthings 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AllOurThings
Household and personal inventory management, backed by a local or cloud-synced vault (iCloud Drive, Dropbox, OneDrive, or any folder).
When to Use
✅ USE this skill when the user asks about:
- Their belongings, possessions, or household items
- Appliances, electronics, tools, furniture, vehicles, collectibles
- Warranties — "is my TV still under warranty?", "what warranties are expiring?"
- Purchase history — "when did I buy my washing machine?", "how much did I pay?"
- Finding something — "where did I put my drill?", "do I own a label maker?"
- Adding or cataloguing a new item
- Searching across their inventory — "list all Bosch appliances"
- Attaching or retrieving photos, receipts, manuals, or warranty documents
When NOT to Use
❌ DON'T use this skill when:
- The user is asking about general product information or reviews (no inventory context)
- The question is about shopping or buying something new (unless checking existing inventory first)
- The vault is not configured — prompt the user to set
ALLOURTHINGS_DATA_DIR
Setup
The user must set ALLOURTHINGS_DATA_DIR to the path of their AllOurThings
vault folder.
# Example — iCloud Drive vault
export ALLOURTHINGS_DATA_DIR="$HOME/Library/Mobile Documents/com~apple~CloudDocs/Documents/allourthings-vault"
# Example — Dropbox
export ALLOURTHINGS_DATA_DIR="$HOME/Dropbox/AllOurThings"
# Example — local folder
export ALLOURTHINGS_DATA_DIR="$HOME/Documents/AllOurThings"
Add this to your shell profile (~/.zshrc, ~/.bashrc) to make it permanent.
The vault is a plain folder of JSON files — create it anywhere you like, or point it at an existing folder to start cataloguing immediately.
Available Tools
| Tool | Description |
|---|---|
list_items |
List all items, optionally filtered by category, subcategory, or tags |
search_items |
Search field values; every word in the query must match |
get_item |
Retrieve a single item by ID or name (errors with the matching IDs if a name is ambiguous) |
add_item |
Add a new item to the vault (names must be unique) |
update_item |
Update fields on an existing item; set a field to null to clear it |
delete_item |
Delete an item and all its attachments |
get_item_fields |
List all field names in use across the vault |
add_attachment |
Attach a base64-encoded photo, receipt, manual, or warranty document (kind is required) |
get_attachment |
Retrieve an attachment's contents as base64 |
attach_from_url |
Download a file from a URL and attach it to an item |
delete_attachment |
Remove an attachment from an item |
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.
- 7d ago Changed d49f88e900e3
- 2mo ago First seen · 137 lines · 93 tokens per session scan A 692811b56927
allourthings is a skill published in the GitHub repository matt-harding/allourthings-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 93 tokens to every session and 1,182 once invoked, about $0.0004 per session on Opus 5.5. 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
specimen-authoring
Workflow and hard-won TD patterns for authoring Embody Specimens (the transparent TDXN gallery networks). Load before building or persisting a Specimen.
externalize-operator
MUST READ before calling externalizeop or saveexternalization. Required workflow steps.
multi-instance
Workflow for running multiple TD instances with Envoy, switching between them, and understanding the instance registry.
getting-started
Connect Taskade and show the user what they can do with it. Use when the user says "set up Taskade", "connect Taskade", "what can you do in Taskade", "what is in my Taskade workspace", or when a Taskade tool fails with a sign-in or plan error.
coding-flow
Light coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.