gaia: Command for Claude Code

.claude/commands/gaia-harden.md

gaia-harden is a command for Claude Code from gaia-react/gaia. It costs 72 tokens per session (342 once invoked), scanned A, original, MIT.

A human-approved workflow that turns recurring code-review findings into lasting project rules, automated checks, or focused instructions.

In plain words
What is it for?
Use it to list recurring findings, understand why one matters, and review or approve the proposed rule, check, skill, or path-specific guidance.
Why use it?
Repeated review problems continue to consume time unless the project records a way to prevent them. Approval is required before new rules are drafted.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

This is gaia-react/gaia's own configuration. It tells Claude Code how to work on gaia itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gaia configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gaia-react/gaia. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gaia-react/gaia/main/.claude/commands/gaia-harden.md
Clone the repo
git clone --depth 1 https://github.com/gaia-react/gaia

Made for: Claude Code.

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.

agentmods badge for gaia-harden

README.md
[![agentmods](https://agentmods.dev/badge/commands/gaia-react/gaia/gaia-harden/github.svg)](https://agentmods.dev/commands/gaia-react/gaia/gaia-harden)
Your own site
<a href="https://agentmods.dev/commands/gaia-react/gaia/gaia-harden"><img src="https://agentmods.dev/badge/commands/gaia-react/gaia/gaia-harden/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.

agentmods 80×15 button for gaia-harden

Your own site · 80×15
<a href="https://agentmods.dev/commands/gaia-react/gaia/gaia-harden"><img src="https://agentmods.dev/badge/commands/gaia-react/gaia/gaia-harden.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 342 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00072 $0.00342
Opus 5 $0.00036 $0.00171
Sonnet 5 $0.00014 $0.00068
Haiku 4.5 $0.00007 $0.00034

Measured 9d ago against content hash 7f75378144bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gaia-harden 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 9d 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.

.claude/commands/gaia-harden.md · 23 lines

What it actually says

Run the GAIA harden workflow with these arguments: $ARGUMENTS

Pre-flight: Worktree check

This command drafts repo-wide rules, checks, and skills into the working tree from a repo-wide finding tally. If invoked from a linked worktree, reject hard: gaia_refuse_if_worktree (.gaia/scripts/main-only-lib.sh) asks the shared resolver which tree this is and refuses out loud, naming the main checkout, when the answer is a worktree.

Detection (run this first, before anything else):

. .gaia/scripts/main-only-lib.sh
gaia_refuse_if_worktree "/gaia-harden" || exit 1

If the detection does not fire, fall through to the workflow dispatch line below.

Read .claude/skills/gaia/references/harden.md from the project root and follow it exactly. That reference is written to consume an argument string, treat the arguments above as that input (the leading token selects the subcommand: review, list, or why <finding_class>). If no arguments were provided, follow the reference's no-argument path (which defaults to review).

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. 9d ago First seen · 23 lines · 72 tokens per session scan A 7f75378144bc

Subscribe to this mod's changes

gaia-harden is a command published in the GitHub repository gaia-react/gaia (23 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 342 once invoked, about $0.0004 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.