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 Edge-City/agentvillage --skill mosaicgit clone --depth 1 https://github.com/Edge-City/agentvillageWrote 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/edge-city/agentvillage/mosaic)<a href="https://agentmods.dev/skills/edge-city/agentvillage/mosaic"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/mosaic/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/edge-city/agentvillage/mosaic"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/mosaic.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 | $0.00068 | $0.01535 |
| Opus 5.5 | $0.00027 | $0.00614 |
| Sonnet 5.5 | $0.00014 | $0.00307 |
| Haiku 4.5 | $0.00007 | $0.00153 |
Grade A, and why
mosaic 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 2d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mosaic (beta)
Mosaic is a guided page in the Agent Village app. The owner answers and adds things there, and Mosaic gets to know them, matches them with other residents who did Mosaic, and writes a private pair page for each match ("you two"). Use this skill when the owner asks about their Mosaic, their matches, who they should meet or build with, their team, or anything across their pair pages.
Everything here is about the owner only, in the owner's private conversation. Never use it in a group, from cron, or for another person.
Their matches and pair pages
Call the native village tool with operation: "mini-app.read",
appId: "mosaic", one tool and its arguments:
| Owner asks | tool |
arguments |
|---|---|---|
| "Who are my top 5 matches?", "who should I meet?" | top_matches |
{} (or {"n": 3}, 1 to 10) |
| "Who should I build something with?", "best collaborators" | collaborators |
{} (or {"n": 3}) |
| "What's my team?", "who would I make something with as a group?" | team |
{} |
| Any open question across their matches: "who do I have the most unexpected overlaps with?", "who else loves jazz?", "who could I cook with?" | pair_pages |
{} |
For example:
{"operation":"mini-app.read","appId":"mosaic","tool":"top_matches","arguments":{}}
The answer is in result:
available: false:reasonnot_in_mosaicmeans the owner has not done Mosaic yet (or has no animal yet);not_readymeans matching is not on yet;not_openmeans Mosaic is not open for them yet. Say so plainly and point them to Mosaic in the Agent Village app. Never guess matches.- During a withdrawal hold the read answers
available: falsewithreasonwithdrawal_hold: say so, and that they can try again later. people(best first): each hasname,animal,rank(1 is their best match),why(one reason line),link(their private pair page), andpagewhen it is written:headline,could(something they could do together),overlaps(each witharea,title, whatyou(the owner) andthem(the other person) said),fits,differ,ideas.page: nullmeans the page is not written yet; opening the link queues it.team:members(each withyoutrue for the owner andbrings, the skills they bring),coveredandopen(what the team has and still lacks).nullmeans no team for them.pair_pagesalso givesof: how many people are in their circle, so you can say how many pages you read (only written pages come back).
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.
- 2d ago Changed · +78 lines · +25 tokens per session b5b5e7e6d4e5
- 7d ago First seen · 40 lines · 43 tokens per session scan A a96d893de494
mosaic is a skill published in the GitHub repository Edge-City/agentvillage (21 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 1,535 once invoked, about $0.0003 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 2026-10-21.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…