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 monoes/monomind --skill mastermind-plugin-managergit clone --depth 1 https://github.com/monoes/monomindWrote 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/monoes/monomind/mastermind-plugin-manager)<a href="https://agentmods.dev/skills/monoes/monomind/mastermind-plugin-manager"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-plugin-manager/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/monoes/monomind/mastermind-plugin-manager"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-plugin-manager.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 | $0.00042 | $0.02437 |
| Opus 5.5 | $0.00017 | $0.00975 |
| Sonnet 5.5 | $0.00008 | $0.00487 |
| Haiku 4.5 | $0.00004 | $0.00244 |
Grade A, and why
mastermind-plugin-manager scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
latest=$(curl -sf "https://registry.npmjs.org/${pkg}/latest" 2>/dev/null | jq -r '.version // "?"' 2>/dev/null || echo "?") How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind Plugin Manager
This skill is invoked directly via /mastermind-plugin-manager.
Bookkeeping only — not enforced by the Org Runtime. It writes .monomind/plugins/registry.json, which no runtime code reads: installing, enabling, or disabling a plugin here does not load or unload anything.
Inputs
brain_context: BRAIN CONTEXT block (injected by command, or loaded below if standalone)action: list | install | uninstall | enable | disable | check-updatespackage_name: npm package name to install (for install; e.g.@monomind/plugin-github)plugin_id: plugin id slug (required for uninstall/enable/disable)confirm: yes (required second step for uninstall — prevents accidental removal)caller: command | master
Plugin Record Schema
{
"id": "plugin-slug",
"packageName": "@monomind/plugin-name",
"status": "installed",
"version": "1.2.0",
"category": "monitoring",
"description": "One-line plugin description",
"installedAt": "2026-01-01T00:00:00Z",
"config": {},
"grants": [],
"health": {"status": "ok", "lastCheck": null}
}
Step 0 — Brain Load (standalone only)
If caller is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: ops.
Step 1 — Load Plugin Registry
registryFile=".monomind/plugins/registry.json"
mkdir -p ".monomind/plugins"
[ ! -f "$registryFile" ] && echo '{"plugins":[]}' > "$registryFile"
Step 2 — Execute Action
list (default)
echo "INSTALLED PLUGINS"
echo "────────────────────────────────────────────────────────"
printf "%-24s %-10s %-10s %-14s %s\n" "ID" "STATUS" "VERSION" "CATEGORY" "PACKAGE"
echo "────────────────────────────────────────────────────────"
count=$(jq '.plugins | length' "$registryFile")
if [ "$count" -eq 0 ]; then
echo " No plugins installed."
echo " Install one: --action install --package-name @monomind/plugin-github"
else
jq -r '(.plugins // [])[] |
[.id, (.status // "installed"), (.version // "-"), (.category // "general"),
(.packageName // "-")] | @tsv' \
"$registryFile" | while IFS=$'\t' read -r id st ver cat pkg; do
printf "%-24s %-10s %-10s %-14s %s\n" "$id" "$st" "$ver" "$cat" "$pkg"
done
errCount=$(jq '[(.plugins // [])[] | select(.status == "error")] | length' "$registryFile")
[ "$errCount" -gt 0 ] && echo "" && echo " WARNING: $errCount plugin(s) in error state. Run: --action list to inspect."
fi
echo ""
echo " Install: --action install --package-name <npm-package>"
echo " Uninstall: --action uninstall --plugin-id <id>"
echo " Settings: /mastermind-plugin-settings --plugin-id <id>"
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 First seen · 245 lines · 42 tokens per session scan A 1dc30ec2809c
mastermind-plugin-manager is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 42 tokens to every session and 2,437 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
Other skills, from other repositories
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
mailbox
A guide for performing email and mailbox tasks through the QwenPaw mailbox system. It covers supported personal email providers, credentials, configuration, and the required mailbox workflow.
channel_message
Use this skill to proactively send a one-way message to a user/session/channel, usually only when the user explicitly asks to send to a channel/session or when proactive notification is needed. First query sessions with qwenpaw chats list, then push with qwenpaw channels send.
mission-slice-sop
Use when starting, building, handing off, restoring, or closing a mission or slice under the default lightweight SDLC.
oma-recap
Summarize AI conversation histories for a specified date or period. Use for daily work recaps and cross-tool activity summaries.
todos
Handle the agent personal todos.md file.