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 skills/metraton/gaia/executionnpx skills add metraton/gaia --skill executiongit clone --depth 1 https://github.com/metraton/gaiaWhat 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 | $0.00020 | $0.00427 |
| Opus 5 | $0.00010 | $0.00214 |
| Sonnet 5 | $0.00004 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
execution 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 yesterday.
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
Approved Execution
Approval resumes work in a fresh dispatch owned by the relevant specialist. It does not turn the orchestrator into an executor and does not broaden scope.
Source boundary
For Gaia components, edit only the canonical gaia/ source tree. Never write,
copy, generate, or stage anything under .claude/; installation propagates
source changes. The same prohibition applies to fixtures and bulk operations.
Ordered execution
- Read the granted request from the trusted handoff/DB and confirm its exact id, scope, order, and next unconsumed index.
- Execute exactly one command per tool call using
command-execution. - For COMMAND_SET, run only the exact next index. Never join commands, skip an index, substitute an equivalent spelling, or add an unapproved command.
- After every result, checkpoint the exact command, index, exit status, and runtime progress fields when exposed.
- On failure, stop immediately. Record stderr/stdout, failed index, completed
indexes, remaining unexecuted indexes, and the state uncertainty. The grant
is terminal/frozen
FAILED; neither retry nor remainder may execute under it. Grouping consent is not atomicity or a continue-on-error policy. - After successful mutations, verify desired state with separate read-only checks. Success exit codes alone are insufficient.
- Checkpoint verification and emit
NEEDS_VERIFICATIONfor a plan-task-bound producer; only an eligible unbound turn/verifier may reachCOMPLETE.
After any COMMAND_SET failure, fresh investigation must establish the actual partial state. Every retry and every still-needed remainder command is a new plan: collect them into a new exact request-set (or a singular request when only one remains) and obtain new approval. Unused items in the frozen grant do not authorize execution, even when their bytes are unchanged.
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.
- yesterday First seen · 40 lines · 20 tokens per session scan A 2a4ad2c86a46
execution is a skill published in the GitHub repository metraton/gaia (3 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 427 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
trigger-authoring-tasks
Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…