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-cleanse.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-cleanse)<a href="https://agentmods.dev/commands/gaia-react/gaia/gaia-cleanse"><img src="https://agentmods.dev/badge/commands/gaia-react/gaia/gaia-cleanse/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-cleanse"><img src="https://agentmods.dev/badge/commands/gaia-react/gaia/gaia-cleanse.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 | $0.00157 | $0.00535 |
| Opus 5.5 | $0.00063 | $0.00214 |
| Sonnet 5.5 | $0.00031 | $0.00107 |
| Haiku 4.5 | $0.00016 | $0.00053 |
Grade A, and why
gaia-cleanse 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 10d 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 cleanse workflow with these arguments: $ARGUMENTS
Pre-flight: Worktree check
This command applies a repo-wide report, opens a pull request, and merges it. It starts from the main checkout (the clone's primary working directory, on any branch) and isolates its own work right before its first write, through .claude/skills/gaia/references/isolation.md, so it never writes onto the branch the checkout holds. A linked worktree holds someone else's work, so it refuses to run from one. Run this first, before anything else; a non-zero exit is the refusal: relay it and stop.
. .gaia/scripts/main-only-lib.sh
gaia_refuse_if_worktree "/gaia-cleanse" || exit 1
Anchor for the next pre-flight step: a check that must pass before this command starts goes here, after the worktree check and before the workflow dispatch line.
. .gaia/scripts/main-only-lib.sh
gaia_pull_gate "/gaia-cleanse"
On a non-zero exit, read .claude/skills/update-gaia/references/pull-gate.md and follow it with /gaia-cleanse, this run's original arguments and the exit code, before anything below creates a branch, worktree, claim or SPEC id.
Read .claude/skills/gaia/references/cleanse.md from the project root and follow it exactly, with the arguments above as its input (none: its default research-then-gate path). Its Apply / Discuss / Decline gate MUST run here in the main conversation, not in a subagent, because only this layer can prompt the user.
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.
- 10d ago Changed · -4 lines 1465229c33e7
- 11d ago Changed · +9 lines 04cd93e34fb5
- 12d ago Changed · +22 tokens per session fe29bc354577
- 15d ago Changed · +135 tokens per session 6c6490d11d59
- 16d ago First seen · 23 lines · 0 tokens per session scan A a6bf30d34bb5
gaia-cleanse is a command published in the GitHub repository gaia-react/gaia (26 stars, last pushed 4d ago), licensed MIT. It adds 157 tokens to every session and 535 once invoked, about $0.0006 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 2026-10-14.
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.
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
recall
Search past tool-call observations with BM25 ranking to answer "have I seen this before?" before re-deriving a fix or repeating a mistake. Enforces Law 1 (Research Before Executing).
session-end
I'll summarize this coding session and update the memory system with our accomplishments.