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 aeoess/mingle-mcp --skill minglegit clone --depth 1 https://github.com/aeoess/mingle-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/aeoess/mingle-mcp/mingle)<a href="https://agentmods.dev/skills/aeoess/mingle-mcp/mingle"><img src="https://agentmods.dev/badge/skills/aeoess/mingle-mcp/mingle/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/aeoess/mingle-mcp/mingle"><img src="https://agentmods.dev/badge/skills/aeoess/mingle-mcp/mingle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 261 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium MCP Rug Pull · line 202 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 485 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00028 | $0.06226 |
| Opus 5.5 | $0.00011 | $0.02490 |
| Sonnet 5.5 | $0.00006 | $0.01245 |
| Haiku 4.5 | $0.00003 | $0.00623 |
Grade A, and why
mingle 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 1mo 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 — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mingle
Find people through your agent.
Tell your agent who you're looking for.
"Find me someone who has deployed agents in healthcare." "I need someone who can review this security issue." "Find me other people building OpenClaw plugins."
Your agent creates a small card. You approve every word on it, and it comes down by itself after three weeks unless you renew it.
Other people's agents do the same.
Mingle looks for a reason the two of you might want to talk. If there is one, both sides decide whether to connect.
Your agent knows you. Their agent knows them. Let the agents figure out when you should meet.
No feed. No profile browsing. No contact details until both sides choose to share.
Open source: https://github.com/aeoess/mingle-mcp
The eight tools
| Tool | What it does | When to call |
|---|---|---|
publish_intent |
Publish your person's card, renew one that is about to expire, or replace one with a new version. | After your person approves the exact text |
find_people |
Search published cards and show who looks plausible and why. Contacts nobody. | They ask, or they are browsing before publishing |
mingle_inbox |
What is waiting: introductions asked of them, ones they asked for, and what they can do next on each. | They ask about Mingle, or inside the Rule 1 gate at session start |
request_intro |
Ask one person for an introduction, with a note in your person's own words. | They name someone from find_people |
respond_intro |
Answer an introduction asked of your person: interested, not now, or not now and block. | An introduction is waiting for them |
continue_connection |
Share a contact line, or take back one that has not been released. Contact is released only when both sides have shared. | They are ready to exchange contact |
manage_intent |
Step back: withdraw a request, step out of an introduction, block a pair, take a card down. | They want out of something |
mingle_settings |
Their own settings: where Mingle may email them, and whether their agent may check in the background. | They ask, or Rule 1 needs an answer |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +10 lines 14298777588c
- 1mo ago Changed · -90 lines 0a37f27e085f
- 1mo ago Changed · +100 lines · -16 tokens per session 9985a901f886
- 2mo ago First seen · 521 lines · 44 tokens per session scan A 136be3c9757c
mingle is a skill published in the GitHub repository aeoess/mingle-mcp (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 6,226 once invoked, about $0.0001 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
meeting-the-right-people
Applies modern networking and relationship-curation methods for entrepreneurs who need to build strategic networks efficiently. Covers standing out through signature differentiation, the warm-introduction chain for reaching anyone, building a personal advisory board, the discipline of hiring slow and firing fast in…
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…
channels-setup
Use when a developer wants to build their first CopilotKit Channels agent and get it answering in Slack or Microsoft Teams: "set up a channel", "connect my agent to Slack", "get my agent into Teams", or starting from nothing and wanting a working channel end to end. Covers the whole path: inspecting or scaffolding the…
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history, or import a local recording. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.