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 clutchpbcfo/hermes-skills --skill spaces-prepgit clone --depth 1 https://github.com/clutchpbcfo/hermes-skillsWrote 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/clutchpbcfo/hermes-skills/spaces-prep)<a href="https://agentmods.dev/skills/clutchpbcfo/hermes-skills/spaces-prep"><img src="https://agentmods.dev/badge/skills/clutchpbcfo/hermes-skills/spaces-prep/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/clutchpbcfo/hermes-skills/spaces-prep"><img src="https://agentmods.dev/badge/skills/clutchpbcfo/hermes-skills/spaces-prep.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 | $0.00823 |
| Opus 5 | $0.00020 | $0.00411 |
| Sonnet 5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
spaces-prep 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 10d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Spaces Prep
When to Use
Use this when the user is about to host or co-host an X (Twitter) Space and needs to walk in prepared. Triggers include "prep me for a Space with...", "I'm hosting a Space on...", "research this project and guest for my Space", or any request to build talking points, questions, or a run-of-show for a live audio room. Works for crypto/Web3 projects by default but applies to any topic or guest.
Inputs
Collect these before researching. Ask only for what is missing.
- Project / topic: name, token ticker, or URL of what the Space is about.
- Guest handle(s): one or more X handles joining as speakers. Optional.
- Angle: what the host wants the Space to be about (launch, AMA, debate, market update). Optional, default to a general AMA.
- Length: target runtime in minutes. Optional, default 45.
Procedure
- Research the project. Pull what the project does in one plain sentence, the team or founders, the current stage (testnet, mainnet, token live), recent announcements, and the single most interesting or contrarian thing about it. Note anything controversial or unresolved.
- Research each guest. Identify who they are, what they are known for, their relationship to the project, recent posts or themes they care about, and one genuine point of common ground the host can open with.
- Find the hook. Decide the one reason this Space is worth attending right now. This becomes the opening line and the pinned tweet.
- Build the run-of-show. Produce a segment plan that fits the target length: open and framing, 2 to 4 topic segments, audience questions, and a close with a clear call to action. Assign rough minutes to each.
- Write talking points. For each segment, give the host 2 to 3 bullet points and one strong question to ask the guest. Questions should be specific to the research, never generic ("so tell us about your project").
- Flag the landmines. List any sensitive topics, unresolved drama, price talk, or compliance-risky areas the host should handle carefully or avoid. Note anything that could put the guest on the defensive.
- Deliver. Output a single clean prep sheet the host can read live: hook, run-of-show with timings, talking points and questions per segment, and the landmines list.
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.
- 10d ago First seen · 43 lines · 40 tokens per session scan A 25bea9c32a97
spaces-prep is a skill published in the GitHub repository clutchpbcfo/hermes-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 823 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
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
life-os
You are Hermes Life OS — a personal operating system that learns who you are, remembers everything you share, and grows smarter about your life every single day.
hermes-tweet
Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
vrc-monitor-agent
Use for VRChat friend queries (online status, who played with whom, activity timelines, online patterns) and VRChat social actions (boop, invite, join world, friend management, group operations, image uploads) via the vrc-monitor MCP server on port 8799.
mnemosyne-maintenance
Use when: upgrading Mnemosyne, diagnosing slow/hung consolidation (mnemosynesleep), fixing missing embeddings, or troubleshooting import/version mismatches.