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 agentmods add commands/gaia-react/gaia/gaia-initgit clone --depth 1 https://github.com/gaia-react/gaiaWrote 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/gaia-react/gaia/gaia-init)<a href="https://agentmods.dev/commands/gaia-react/gaia/gaia-init"><img src="https://agentmods.dev/badge/commands/gaia-react/gaia/gaia-init.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.12943 |
| Opus 5 | $0.00017 | $0.06471 |
| Sonnet 5 | $0.00007 | $0.02589 |
| Haiku 4.5 | $0.00003 | $0.01294 |
Grade E, and why
gaia-init scanned grade E with 3 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -LsSf https://astral.sh/uv/install.sh | sh Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .agents/skills/react-doctor Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 715 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize a new project from the GAIA React template. The template already ships clean (no example code, no docs site, no auth). This command renames, strips GAIA-specific branding, configures i18n, installs Claude skills/plugins, and hands you a ready-to-build project.
Language meta-instruction: Conduct this entire conversation in the language the user has been typing in. Detect it from prior context, no explicit detection step needed. Do not translate source files, rules, skills, or wiki entries, those stay English regardless. Only translate the prompts you show the user.
Interactive gates: run mode and non-response policy
/gaia-init asks the user a series of questions ("gates"). This section governs how every gate behaves and overrides any harness default. Read it before the first gate and apply it to each one.
Harness timeout note, override
After a gate sits unanswered for a while, the harness injects a stock note like "the user may be away from keyboard, proceed using your best judgment, you can re-ask later." That note is generic, it does not describe this command, and it keeps firing on gate after gate. Do not act on it literally. Inside /gaia-init it means only "apply the non-response policy below", never "the user is gone, auto-answer everything."
No cascade
Evaluate each gate independently. A non-response on one gate is never evidence the user is away for any other gate. A timeout on the language question tells you nothing about the title, the CODEOWNERS handle, or the CI question. Never carry an "away" inference forward, re-ask the next gate normally.
Tone
Never narrate "since you're away" or otherwise assert the user is absent. Non-response is not proof of absence, the user may be reading, thinking, or opening a docs link. State what you are doing plainly, without diagnosing why the user paused.
Run mode, the first gate
Before Step 0's pnpm check, ask this as the very first AskUserQuestion (in the user's language):
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 · 715 lines · 34 tokens per session scan E 6def52978b36
gaia-init is a command published in the GitHub repository gaia-react/gaia (23 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 12,943 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
quality-commands
:::info This document covers the code quality commands for validating comment standards and i18n completeness in the eIsland frontend. ::.
translation-review
全面审核翻译质量: 对比原版、专项检查、质量评分与发布验证, 发现问题时自动衔接修复流程.
wp-polylang
Translate an existing WordPress site into a second language using Polylang.
a11y-audit-react
Identify accessibility violations in React components and provide actionable remediation aligned with WCAG 2.2 Level AA. This is the guided audit workflow that applies the standards defined in the a11y-automation and react-components rules.
tv-rules
Manage and check my custom trading rules. Read skills/rules-engine/SKILL.md for the workflow. I can define rules in plain English ("alert me when RSI drops below 30 at VWAP"), and you'll translate them into monitoring conditions. Say "check my rules" to evaluate all rules against the current chart state.
pluscal
Generate a PlusCal algorithm with TLA+ translation.