A command that activates named AI reasoning roles for a mathematical research project. It reads the project's instructions and documents before running one role, a phase, or all available roles.

Use it to run a specific named research role, all roles in one phase, or the complete sequence for the Riemann-hypothesis project.

It provides a defined way to examine a research problem from different assigned perspectives while grounding the work in the project's existing notes.

mind — Command for coding agents by rana: A command that activates named AI reasoning roles for…

Install

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.

agentmods

npx agentmods add commands/rana/skills/mind

Clone the repo

git clone --depth 1 https://github.com/rana/skills

Or install y, the plugin that ships this one along with the rest of its 64 skills, 14 commands, 8 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/rana/skills/mind.svg)](https://agentmods.dev/commands/rana/skills/mind)

Your own site

<a href="https://agentmods.dev/commands/rana/skills/mind"><img src="https://agentmods.dev/badge/commands/rana/skills/mind.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 579 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00579
Opus 5	$0.00000	$0.00290
Sonnet 5	$0.00000	$0.00116
Haiku 4.5	$0.00000	$0.00058

Measured 4d ago against content hash 27f2b157ae2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mind 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 4d 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.

commands/mind.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Activate an AI-native cognitive architecture for mathematical research.

$ARGUMENTS

Mode

Parse the argument.

No argument → Error: "Mind needs a name. Example: /mind adversary. See riemann-hypothesis/MINDS.md for the designed minds."
"all" → Run all minds following the execution protocol in MINDS.md (phased, with dependencies).
A phase number (1-5) → Run all minds in that phase.
Any other argument → The argument is the mind's name. Proceed with single-mind execution.

Execution

Single Mind

Read riemann-hypothesis/MINDS.md and find the section matching the argument (case-insensitive, partial match OK: "adv" matches "Adversary").
If no match found → Error: "Mind '[argument]' not found. Available: Adversary, Simultaneist, Wound, Forgetter, Listener, Bridge, Gradient, Time-Traveler, Geometer, Negator, Self-Aware Reasoner, Archaeologist, Ensemble, Proof Architect."
Extract the mind's Prompt section from MINDS.md.
Read all project markdown documents to ground in the project's actual state. Follow the reading order in CLAUDE.md. Read PROOF-GRAPH.md, ALIVE.md, RETURNED.md, APPROACHES.md.
Execute the extracted prompt with full grounding. The prompt IS the cognitive task — follow it precisely.

All Minds / Phase

Follow the execution protocol in MINDS.md:

Phase 1 runs first (Forgetter)
Phase 2 runs in parallel (Adversary, Listener, Wound, Geometer, Negator)
Phase 3 runs in parallel after Phase 2 (Bridge, Time-Traveler)
Phase 4 runs sequentially after Phase 3 (Simultaneist, Gradient)
Phase 5 runs sequentially after Phase 4 (Self-Aware Reasoner, Archaeologist, Ensemble)

Each mind runs as a subagent. Pass the full prompt from MINDS.md. Each subagent reads the knowledge architecture independently.

Output

Write each mind's output to the report path specified in MINDS.md: riemann-hypothesis/reports/YYYY-MM-DD-[mind-name]-mind.md

Prepend frontmatter:

---
title: "[Mind Name]: [brief description of what emerged]"
date: YYYY-MM-DD
type: mind
status: active
mind: "[mind-name]"
phase: [1-5]
---

Read the full file on GitHub · 61 lines

Changes

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.

4d ago First seen · 61 lines · 0 tokens per session scan A 27f2b157ae2e

Subscribe to this mod's changes

mind is a command published in the GitHub repository rana/skills (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 579 tokens. 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.

Code review Planning Research ai-agents architecture-decisions claude-code claude-code-plugin cognitive-tools

mind

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Mode

Execution

Single Mind

All Minds / Phase

Output

What this file has done since we first saw it

Other commands, from other repositories

init

brand-generate

genshijin-compress

standup

wp-polylang

check-dev