Gaia Submission

What it does

Example prompts

• “/gaia-submission”

Requirements

• Node.js
• A credential in ANTHROPIC_API_KEY
• Pre-approved tools (allowed-tools): Bash, mcp__plugin_ruflo-core_ruflo__memory_store, mcp__plugin_ruflo-core_ruflo__memory_search, mcp__plugin_ruflo-core_ruflo__memory_list, mcp__plugin_ruflo-core_ruflo__hooks_post_task, mcp__plugin_ruflo-core_ruflo__hooks_pre_task

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Validate environment
2. 2Estimate cost and confirm
3. 3Run the benchmark
4. 4Package for submission
5. 5Compare and report
6. 6Persist learnings

What it can do on your machine

Read from SKILL.md and the folder at commit 6c04654. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • mcp__plugin_ruflo-core_ruflo__memory_store
  • mcp__plugin_ruflo-core_ruflo__memory_search
  • mcp__plugin_ruflo-core_ruflo__memory_list
  • mcp__plugin_ruflo-core_ruflo__hooks_post_task
  • mcp__plugin_ruflo-core_ruflo__hooks_pre_task

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npx
  • node

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • ANTHROPIC_API_KEY
  • HF_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gaia Submission loads about 1.2k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 424 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~33

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, mcp__plugin_ruflo-core_ruflo__memory_store, mcp__plugin_ruflo-core_ruflo__memory_search, mcp__

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ruvnet/ruflo at commit 6c04654, republished under its MIT licence (© ruvnet). 424 words, ~1,239 tokens.

name

gaia-submission

description

Walk through a complete GAIA benchmark→submit flow — from key resolution through HAL-compatible package generation

allowed-tools

Bash, mcp__plugin_ruflo-core_ruflo__memory_store, mcp__plugin_ruflo-core_ruflo__memory_search, mcp__plugin_ruflo-core_ruflo__memory_list, mcp__plugin_ruflo-core_ruflo__hooks_post_task, mcp__plugin_ruflo-core_ruflo__hooks_pre_task

argument-hint

[level] [limit] [models]

# Run all pre-flight checks
/gaia validate

/gaia cost --level=$LEVEL --limit=$LIMIT --models=$MODELS --voting=$VOTING

/gaia run --level=$LEVEL --limit=$LIMIT --models=$MODELS --voting=$VOTING

[12/53] 22.7% (5 passed of 22 scored) — est. remaining: $0.18

npx @claude-flow/cli@latest memory store \
  --namespace gaia-runs \
  --key "run-$(date +%Y%m%d-%H%M)" \
  --value '{"level":$LEVEL,"model":"$MODEL","total":$TOTAL,"passed":$PASSED,"pass_rate":$RATE,"est_cost_usd":$COST}'

/gaia submit --results=~/.cache/ruflo/gaia/results-latest.json

submission-<date>-<sha>/
├── results.jsonl        ← HAL-compatible, one JSON per line
├── trajectories.jsonl   ← full agent traces
├── metadata.json        ← harness info, model, tool catalogue
├── audit-report.json    ← ADR-167 pre-submission exploit-audit report
├── manifest.md.json     ← Ed25519-signed witness (signs audit-report.json's hash)
└── README.md            ← human summary + leaderboard comparison

/gaia leaderboard --level=$LEVEL
/gaia history

npx @claude-flow/cli@latest hooks post-task \
  --task-id "gaia-submission-$(date +%Y%m%d)" \
  --success true \
  --train-neural true

npx @claude-flow/cli@latest memory store \
  --namespace gaia-patterns \
  --key "submission-notes-$(date +%Y%m%d)" \
  --value "Level $LEVEL, $MODEL: $NOTES"

© ruvnet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/ruflo-workflows/skills/gaia-submission of ruvnet/ruflo.

Open the folder on GitHubat commit 6c04654