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 AtlasOmnia/hermes-custom-pack --skill local-discoverygit clone --depth 1 https://github.com/AtlasOmnia/hermes-custom-packWrote 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/atlasomnia/hermes-custom-pack/local-discovery)<a href="https://agentmods.dev/skills/atlasomnia/hermes-custom-pack/local-discovery"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/local-discovery/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/atlasomnia/hermes-custom-pack/local-discovery"><img src="https://agentmods.dev/badge/skills/atlasomnia/hermes-custom-pack/local-discovery.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 | $0.00040 | $0.02851 |
| Opus 5 | $0.00020 | $0.01425 |
| Sonnet 5 | $0.00008 | $0.00570 |
| Haiku 4.5 | $0.00004 | $0.00285 |
Grade A, and why
local-discovery 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.
This is a copy
100% identical to local-discovery — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local & National Discovery
Find events, activities, venues, and things happening in the user's area (default: the user's local area) or anywhere nationally. Covers two subdomains:
- Events — concerts, festivals, comedy, things to do tonight/this weekend
- Venues — bars, lounges, restaurants, nightlife spots matching specific criteria (vibe, amenities, atmosphere)
When to Use
- User asks about local events, things to do tonight/this weekend
- "What's happening around here?" or similar discovery requests
- User asks for venue recommendations with specific criteria (e.g., "cigar lounge," "speakeasy," "classy bar") — local OR national
- User asks "find me X somewhere" without specifying a city — treat as national search
- Need to surface relevant activities based on user interests
Venue Discovery Workflow
When the user asks for venues rather than events, use this approach:
1. Start with Google Maps for venue discovery (PRIMARY TOOL)
Navigate directly to Google Maps search:
browser_navigate(url="https://www.google.com/maps/search/cigar+lounge+near+<city>+<state>")
Google Maps works reliably even when Google Search CAPTCHAs. Returns listings with ratings, review counts, addresses, hours, phone numbers, and user-submitted photos. Click individual venues for detailed info, reviews, and photos (use "Vibe" photo filter for atmosphere shots).
2. Fall back to web_search if needed
Search using specific criteria keywords (e.g., "cigar lounge", "speakeasy bar"). Collect names, addresses, and phone numbers from search results.
PITFALL: web_search relies on ddgs which is installed in the system Python (~/Library/Python/3.9/...) but Hermes runs from a venv that doesn't see it. If you get "ddgs package is not installed", skip to step 3 immediately — don't retry or try to reinstall. This is a persistent env path issue, not transient.
3. Skip review aggregator sites for browser navigation — they CAPTCHA aggressively
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 · 197 lines · 40 tokens per session scan A 63db6f197de7
local-discovery is a skill published in the GitHub repository AtlasOmnia/hermes-custom-pack (56 stars, last pushed 25d ago), licensed MIT. It adds 40 tokens to every session and 2,851 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to local-discovery, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
config
Use when configuring obshare-cli credentials, checking saved settings, testing connectivity, clearing local config, or setting optional Obsidian bridge values used by the V0.2.0 direct-share stack.
obshare-cli
Use when setting up obshare-cli 0.2.0, reviewing available commands, or choosing the right command for config, upload, permission, history, delete, and the plugin-first direct-share workflow.
agent-dreaming-agnostic
Memory-agnostic background consolidation — reviews sessions, scores candidates, promotes durable insights to the active memory backend (built-in MEMORY.md or Holographic). Three-phase (Light/Deep/Condensation/REM). Run via cron or manually.
upload
Use when uploading a Markdown note to Feishu, optionally applying public or copy/download permissions, or requesting JSON upload results for automation or the Obsidian plugin direct-share flow.
permission
Use when changing Feishu document visibility, copy permissions, or download permissions for an uploaded document token.
delete
Use when removing a Feishu document by token and cleaning the matching entry from local obshare-cli upload history.