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.
git 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/commands/monoes/monomind/do)<a href="https://agentmods.dev/commands/monoes/monomind/do"><img src="https://agentmods.dev/badge/commands/monoes/monomind/do/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/commands/monoes/monomind/do"><img src="https://agentmods.dev/badge/commands/monoes/monomind/do.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 | $0.00029 | $0.05297 |
| Opus 5.5 | $0.00012 | $0.02119 |
| Sonnet 5.5 | $0.00006 | $0.01059 |
| Haiku 4.5 | $0.00003 | $0.00530 |
Grade A, and why
do 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 yesterday.
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 — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repeat Flag Extraction
Before all other parsing: Extract and discard --repeat, --tillend, --maxruns, --wait from $ARGUMENTS so they don't interfere with the command's own argument parser. mastermind:do manages its own task-board-driven loop internally (see end of command) — the REPEAT POSTAMBLE is NOT used. To wrap this command with an external loop, use /mastermind:repeat -- /mastermind:do ....
Argument Parsing
Extract --monotask flag first: If --monotask is present, set USE_MONOTASK=true and remove it. Default: USE_MONOTASK=false.
Parse remaining $ARGUMENTS for the following flags (in any order):
--file <path>— (file mode only) use this specific task file; skip file discovery--space <SPACE_ID>— (monotask mode only) use this space directly (skip space discovery)--board <BOARD_ID>— (monotask mode only) use this task board directly (skip board discovery)--filter <text>— only process tasks whose title contains this text (case-insensitive)--mode <parallel|minimal|sequential>— execution mode (default: ask user)--max-agents <N>— cap total agent spawns per run (default: 20)
If $ARGUMENTS contains none of these flags, treat the entire string as a filter (legacy mode).
Auto-promote to monotask mode: If --space and --board are both present (even without explicit --monotask), set USE_MONOTASK=true — these flags only make sense in monotask mode, so their presence implies it. This ensures old wakeup prompts without --monotask still work correctly.
If USE_MONOTASK=true AND --space and --board are both provided, skip Step 1 entirely and go straight to column discovery on the given board.
Step 0: Check monotask CLI (skip unless --monotask was passed)
Only run this step if USE_MONOTASK=true.
command -v monotask
If not found: attempt cargo install monotask. If cargo missing, tell user to install Rust first and STOP.
Step 1: Find Work
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.
- yesterday First seen · 510 lines · 29 tokens per session scan A 9d6200f1e4bc
do is a command published in the GitHub repository monoes/monomind (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 5,297 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 2026-10-26.
Other commands, from other repositories
multi-repo-swarm
Coordinate AI swarms across multiple repositories, enabling organization-wide automation and intelligent cross-project collaboration.
sync-coordinator
Multi-package synchronization and version alignment with ruv-swarm coordination for seamless integration between claude-code-flow and ruv-swarm packages.
auto-agent
Automatically spawn and manage agents based on task requirements.
jira
Retrieve a Jira ticket, analyze requirements, update status, or add comments. Uses the jira-integration skill and MCP or REST API.
bienvenida
Grupo: Rutina del día a día En una frase: Primera vez post-clone — checklist + mensaje de bienvenida con commands recomendados (incluye /setup si falta estructura). Cuándo: Justo después de clonar o abrir el DT por primera vez; la IA también puede mostrarlo sin invocación si no hay sesión local. Quién: Cualquier…
morning
The coffee report — cross-project map deltas, arrives on its own (scheduled).