github

A developer-only command for a maintainer workflow that handles GitHub issues and pull-request reviews through the gh command-line tool. It routes the work to a specialist and keeps approval decisions with a human.

In plain words
What is it for?
Use it to investigate or fix GitHub issues and review pull requests in the MoAI-ADK maintenance workflow.
Why use it?
It separates repository maintenance from normal project commands and prevents automated actions from bypassing review gates. It is not intended for distribution to end-user projects.

Command for Claude Code

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/modu-ai/moai-adk/github
Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-adk

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 163 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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00163
Opus 5 $0.00013 $0.00081
Sonnet 5 $0.00005 $0.00033
Haiku 4.5 $0.00003 $0.00016

Measured yesterday against content hash 2a2d03abe472, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github 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.

.claude/commands/harness/github.md · 14 lines

What it actually says

[DEV-ONLY] maintainer harness. NOT distributed to user projects. user-owned namespace (moai update preserves it).

Run the github harness. Pure human-gated specialist — no Runner, no manifest (no non-interactive fan-out).

Use the hns-github-specialist subagent with arguments: $ARGUMENTS

The specialist is human-gated: the orchestrator holds every AskUserQuestion gate (PR creation approval, review submission). The specialist returns blocker reports for any user decision.

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.

  1. yesterday First seen · 14 lines · 26 tokens per session scan A 2a2d03abe472

Subscribe to this mod's changes

github is a command published in the GitHub repository modu-ai/moai-adk (1,191 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 163 once invoked, about $0.0001 per session on Opus 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 2026-08-30.