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.
curl -O https://raw.githubusercontent.com/gaia-react/gaia/main/.claude/commands/gaia-spec.mdgit 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-spec)<a href="https://agentmods.dev/commands/gaia-react/gaia/gaia-spec"><img src="https://agentmods.dev/badge/commands/gaia-react/gaia/gaia-spec/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/commands/gaia-react/gaia/gaia-spec"><img src="https://agentmods.dev/badge/commands/gaia-react/gaia/gaia-spec.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 | $0.00099 | $0.00507 |
| Opus 5.5 | $0.00040 | $0.00203 |
| Sonnet 5.5 | $0.00020 | $0.00101 |
| Haiku 4.5 | $0.00010 | $0.00051 |
Grade A, and why
gaia-spec 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 6d 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.
What it actually says
Run the GAIA spec workflow with these arguments: $ARGUMENTS
When the first word of the arguments is reopen, skip spec.md: read .claude/skills/gaia/references/spec/uat-divergence.md and follow its ## Reopen for the SPEC id the next word names.
Read .claude/skills/gaia/references/spec.md from the project root and follow it exactly. Treat the arguments above as the reference's $ARGUMENTS.
spec.md routes each run to these sub-references. Read one only when a line in spec.md says to, and then read the whole file:
.claude/skills/gaia/references/spec/lifecycle.md: step 2's pre-flight sweep..claude/skills/gaia/references/spec/resume.md: step 2, only when the allocator reports a draft and the run is interactive..claude/skills/gaia/references/spec/spec-template.md: step 3's initial draft..claude/skills/gaia/references/spec/clarify-loop.md,.claude/skills/gaia/references/spec/clarify-prompts.mdand.claude/skills/gaia/references/spec/system-prompt.md: step 5's Socratic loop..claude/skills/gaia/references/spec/self-review-dispatch.md: step 6, and step 10's loop back to 6c..claude/skills/gaia/references/spec/audit.mdand.claude/skills/gaia/references/spec/lens-dispatch.md: step 7's adversarial audit..claude/skills/gaia/references/spec/self-review.md: read by the self-review sub-agent, never this thread.
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.
- 6d ago Changed · +2 lines · +19 tokens per session 6af6a587ee6e
- 10d ago Changed 29917bbbf9b6
- 12d ago Changed · -2 tokens per session 615bba5b106b
- 14d ago Changed · +82 tokens per session 61ae2825193f
- 21d ago Changed · +10 lines 98ee5be2d87b
- 23d ago Changed 23047c89b06e
- 2mo ago First seen · 10 lines · 0 tokens per session scan A eaea3c05994f
gaia-spec is a command published in the GitHub repository gaia-react/gaia (26 stars, last pushed 4d ago), licensed MIT. It adds 99 tokens to every session and 507 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other commands, from other repositories
push-changes
If no topic provided, just document the recent changes. If a topic is provided, focus on documenting that topic.
create-PR
Command "create-PR" from bartstc/vite-ts-react-template, covering create a pr against this branch: $arguments, follow these steps and remember.
add-ai-feature
Add an AI capability to this Cloudflare Workers + React app by adapting the repo's templates and examples. Read AIINTEGRATION.md first - it holds the current model IDs and platform facts.
security-audit
Full security pass - verify, validate and harden this repo against its real threat model.
ai-streaming-setup
Set up streaming AI responses with proper error handling.
data-pipeline
Design a batch or streaming data pipeline architecture.