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-new-agentgit 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-new-agent)<a href="https://agentmods.dev/skills/monoes/monomind/mastermind-new-agent"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-new-agent/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-new-agent"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-new-agent.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 | $0.02735 |
| Opus 5.5 | $0.00016 | $0.01094 |
| Sonnet 5.5 | $0.00008 | $0.00547 |
| Haiku 4.5 | $0.00004 | $0.00274 |
Grade A, and why
mastermind-new-agent 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind New Agent
This skill is invoked directly via /mastermind-new-agent.
It writes one role in the Org Runtime shape (RoleSchema in packages/@monomind/cli/src/orgrt/types.ts) — the same shape mastermind-createorg produces — and runs monomind org validate on the result. There is no adapter object, heartbeat or per-role system prompt in the org config: the runtime reads runtime, adapter_config.model, responsibilities, skills and skill_pool.
Inputs
brain_context: BRAIN CONTEXT block (injected by command, or loaded below if standalone)org_name: org to add the agent to (required)action: create | preview | list-roles | list-runtimesagent_id: unique slug for the new agent (required for create; auto-generated if omitted)title: display title for the agent (required for create)responsibilities: what the role does,;-separated (3–6 specific duties — this is the role's briefing and whatassignee: "auto"matches tasks against)runtime: claude | codex | antigravity | kimicode | opencode | vercel (default: claude — leave unset for the default Claude runtime)model: model identifier (default: none — the role runs the newest model for its runtime, resolved when the org runs; see below)max_tokens: optional max output tokens per model call (omit to inherit)reports_to: parent role id in the hierarchy (required — an org has exactly one root role, and that is the boss)skills: comma-separated org-library skill names pinned into the prompt (1–3; found in Step 1.5)skill_pool: comma-separated skill names ortag:<tag>the role may load mid-run withorg_skill_loadbudget_tokens: optional per-role token budget (positive integer; omitted when unset — the role then gets its even share of the org budget)caller: command | master
Runtimes and their latest models
Leave adapter_config.model out unless the user asked for an exact model: an unpinned role runs the newest model of its runtime's default family, resolved when the org runs (latest-models.ts), so it is never older than the newest, while a pin goes stale (org validate warns about an older pin). The table is what an unpinned role resolves to today (resolveModel() in orgrt/session-prompt.ts is the source of truth; if it disagrees with this table, it wins). Claude Fable and GPT Astra models are never assigned or routed; the role is rejected if one is named:
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 · 220 lines · 40 tokens per session scan A 7d4527ca6b34
mastermind-new-agent is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,735 once invoked, about $0.0002 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 2026-10-26.
Other skills, from other repositories
agent-swarm-issue
Agent skill for swarm-issue - invoke with $agent-swarm-issue.
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
queue-handoff
Use when ending a turn, finishing a slice, blocked on another agent's work, or escalating to a human — durable work handoff via queue items so the system keeps moving across compactions, missed messages, and interruptions. Covers the hot-potato terminal-turn-rule (active work ends by passing the ball, not by going…
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
score-harness
5-dimension scorecard (0-100, grade A/B/C/F) for a scaffolded harness. Dimensions: Repo understanding (25%), Agent usefulness (25%), MCP safety (20%), Test coverage (15%), Publish readiness (15%). Emits a 6-field badges block (score + mcpRisk + 4 booleans) ready for the harness README. Exit 0 A/B, 1 C, 2 F.
verify-witness
Verify the Ed25519 witness manifest of a scaffolded harness. Fast yes/no signature check that proves the publisher signed this exact file set — separate from the full release-readiness umbrella in validate-harness.