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-budgetsgit 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-budgets)<a href="https://agentmods.dev/skills/monoes/monomind/mastermind-budgets"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-budgets/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-budgets"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-budgets.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 | $0.03504 |
| Opus 5.5 | $0.00016 | $0.01402 |
| Sonnet 5.5 | $0.00008 | $0.00701 |
| Haiku 4.5 | $0.00004 | $0.00350 |
Grade A, and why
mastermind-budgets 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind Budgets
This skill is invoked directly via /mastermind-budgets.
The Org Runtime enforces exactly three caps, all in the org definition .monomind/orgs/<org>.json
(schemas: packages/@monomind/cli/src/orgrt/types-role.ts and types.ts; enforcement:
orgrt/budget-closure.ts):
| Field | Scope | What happens at the cap |
|---|---|---|
roles[].budget_usd |
one role, USD | its session closes and its tasks are blocked. Unset = no USD cap for that role |
roles[].budget_tokens |
one role, tokens | same; replaces the role's even split of run_config.budget_tokens |
run_config.budget_tokens |
whole org, tokens | every role's session closes (default 1000000) |
A role's policy.maxUsd / policy.maxTokens, when set, win over budget_usd / budget_tokens.
A budget_usd cap only counts costs the runtime reports. On a runtime with reports_cost: false in
monomind agent scan --json (codex, kimicode, hermes, vercel, …) the role's cost is unknown —
cost_usd: null in org costs --json — so its budget_usd never fires. Cap those roles with
budget_tokens instead.
Caps are per run: a new monomind org run starts at zero spend, --resume keeps it. The coordinator
is warned once when a role or the org passes 80% of a cap.
There is no org-wide USD cap. monomind org run --budget-usd N only refuses to start a run whose
upfront cost estimate exceeds N; it does not stop a run that overspends. To cap an org in dollars,
give every session role its own budget_usd. Never store budgets in a side-car file such as
.monomind/orgs/<org>-budgets.json — the runtime does not read it, so a limit written there is not
enforced.
Inputs
brain_context: BRAIN CONTEXT block (injected by command, or loaded below if standalone)org_name: org to manage budgets for (required)action: show | set | clear | alertagent_id: role id to scope to (optional — omit for the org-widerun_config.budget_tokens)limit_tokens: token cap to set (for set) —roles[].budget_tokens, orrun_config.budget_tokenswithoutagent_idlimit_usd: USD cap to set (for set, requiresagent_id) —roles[].budget_usdrun: run id to read spend from (optional — defaults to the latest run)caller: command | master
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 · 231 lines · 40 tokens per session scan A 5b6bb1ae1faf
mastermind-budgets 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 3,504 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
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
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.
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…
oia-manifest
Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.
repo-genome
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.