Borrowing it
Nothing to install: this file belongs to andrew-yangy/gru-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andrew-yangy/gru-ai/main/.claude/skills/gruai-agents/SKILL.mdgit clone --depth 1 https://github.com/andrew-yangy/gru-aiWrote 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/andrew-yangy/gru-ai/gruai-agents)<a href="https://agentmods.dev/skills/andrew-yangy/gru-ai/gruai-agents"><img src="https://agentmods.dev/badge/skills/andrew-yangy/gru-ai/gruai-agents/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/andrew-yangy/gru-ai/gruai-agents"><img src="https://agentmods.dev/badge/skills/andrew-yangy/gru-ai/gruai-agents.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 | $0.00000 | $0.02868 |
| Opus 5 | $0.00000 | $0.01434 |
| Sonnet 5 | $0.00000 | $0.00574 |
| Haiku 4.5 | $0.00000 | $0.00287 |
Grade A, and why
gruai-agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize gruai Agent Team
Scaffold a variable-sized AI agent team into the current project. This replaces the old gruai init CLI command.
What This Does
- Prompts the user to choose a team size preset (Starter, Standard, Full, or Custom)
- Generates agents with random names for the selected roles
- Creates
.claude/agents/*.mdpersonality files from role templates - Creates
.claude/agent-registry.json(team config -- the game reads this) - Scaffolds
.context/tree (vision, lessons, directives, reports, backlog) - Creates
CLAUDE.mdproject instructions with agent roster - Creates
gruai.config.jsonproject config
Instructions
Step 0: Resolve Package Root
Before reading any templates, resolve the gruai package root directory. This ensures paths work whether gruai is installed via npm, linked locally, or running from source.
GRUAI_ROOT="$(bash "$(npm root)/gru-ai/cli/resolve-pkg-root.sh" 2>/dev/null || bash "cli/resolve-pkg-root.sh")"
All template paths below are relative to $GRUAI_ROOT (e.g., $GRUAI_ROOT/cli/templates/agent-roles/cto.md).
Step 1: Choose Team Size
Ask the user to choose a team size preset. Present these options:
Team size presets:
1) Starter (4 agents: CEO + COO, CTO, Full-Stack)
2) Standard (7 agents: CEO + COO, CTO, CPO, Frontend, Backend, Full-Stack, QA)
3) Full (11 agents: CEO + all roles including CMO, Design, Data, Content)
4) Custom (pick your own roles -- minimum: COO + CTO + 1 builder)
Preset role mappings:
| Preset | Role IDs included |
|---|---|
| Starter (4) | coo, cto, fullstack |
| Standard (7) | coo, cto, cpo, frontend, backend, fullstack, qa |
| Full (11) | coo, cto, cpo, cmo, frontend, backend, fullstack, data, qa, design, content |
| Custom | User selects from full role list |
The agent count shown (4, 7, 11) includes the CEO who is always present.
Custom mode validation: If the user chooses Custom, present the full role list and ask them to enter role IDs as a comma-separated list. Validate their selection:
- Required: COO (
coo) and CTO (cto) must be included. Reject without them. - Minimum 1 builder: At least one non-C-suite role must be included (e.g., fullstack, frontend, backend, data, qa, design, content). Reject if only C-suite roles are selected.
- If validation fails, show the error and re-prompt.
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.
- 12d ago First seen · 208 lines · 0 tokens per session scan A 072657ca4871
gruai-agents is a skill published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,868 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 2026-08-30.
Other skills, from other repositories
diff-driven-docs
Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.
exploration
Two-mode exploration skill: (1) design dialogue — turn rough ideas into validated designs through collaborative interview before planning; (2) spike — throwaway code answering ONE design question, deleted or absorbed, never shipped. Router invokes mode via dispatch context.
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.
plan-review-gate
Use after saving a non-trivial plan or decision RFC when a fail-closed feasibility, completeness, and alignment review must block execution.
planning
Planning discipline for creating execution plans and decision RFCs. Covers task decomposition, context references, validation levels, risk-based testing, ADR format, plan completeness gate, and functionality flow mapping. Loaded by planner agent.