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 kongaharsha/hermes_stack --skill house-inventorygit clone --depth 1 https://github.com/kongaharsha/hermes_stackWrote 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/kongaharsha/hermes_stack/house-inventory)<a href="https://agentmods.dev/skills/kongaharsha/hermes_stack/house-inventory"><img src="https://agentmods.dev/badge/skills/kongaharsha/hermes_stack/house-inventory.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 | $0.00015 | $0.00546 |
| Opus 5 | $0.00008 | $0.00273 |
| Sonnet 5 | $0.00003 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
house-inventory 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
House Inventory
Overview
House Inventory is a disciplined system for cataloging physical assets, tracking container contents (boxes, bags, suitcases), and maintaining a verifiable index of reference imagery. Designed for precision, speed, and consistency.
Prerequisites
- GBrain Setup: This skill requires an initialized
gbrainenvironment. If you do not have one, set it up first:gbrain initor see GBrain Repository. - Inventory File: A valid markdown inventory file at the configured
storage_path.
Workflow
- Cataloging: Extract objects/item descriptions from image uploads or manual text input.
- Container Indexing: Identify the source/target container (e.g., Box #1).
- Validation: Review extracted lists with the user to ensure terminology compliance before write operations.
- Persisting: Use structured
patchoperations to append or update entries while maintaining file integrity.
Format Principles
- Container-First Hierarchy: Every item must belong to a defined container.
### Container: [Name] * **Type:** [Box/Bag/Suitcase] * **Location:** [Storage/Home] * **Reference Photos:** [link1], [link2] * **Items:** [Standardized bulleted list]
Standardized Terminology
- Consistency: Use precise naming conventions (e.g., "Diyas" over "Mats").
- Renaming: If descriptive terms are identified as inaccurate post-cataloging, perform an immediate refactor of the inventory entry to ensure future search accuracy.
Reliability Patterns
- Atomic Patching: All modifications to the inventory file must be done via
patchoperations to prevent data loss. - Read-Before-Write: Must read current
house-inventory.mdstate prior to execution to prevent conflicts with other agents.
Anti-Patterns
- Hardcoded Pathing: Never assume absolute local file paths outside of the
storage_pathconfiguration. - Vision Guessing: Never assume item identity from low-confidence image analysis. If ambiguous, trigger a manual verification request to the user.
- Cluttered Indexing: Do not create duplicate container entries; always verify existence before cataloging new items.
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 First seen · 47 lines · 15 tokens per session scan A 0ee40d53f4b6
house-inventory is a skill published in the GitHub repository kongaharsha/hermes_stack (5 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 546 once invoked, about $0.0001 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
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…
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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.