air-gapped-helm-handover

air-gapped-helm-handover is a command for Claude Code from PostOakLabs/ainumbers. It costs 32 tokens per session (442 once invoked), scanned A, original, MIT.

A procedure for running and checking a CECL allowance workflow on a local Helm service. CECL, or current expected credit loss, is an accounting estimate of likely loan losses.

In plain words
What is it for?
It is for testing an allowance workflow, comparing dry-run and real-run results, checking execution records, and exporting a verified evidence bundle after a human provides consent.
Why use it?
It guides the agent through dry runs, real runs, verification, and the required human consent step before exporting evidence. This helps distinguish an approved, reproducible result from an unapproved export.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Part of the ainumbers plugin — 1 skill, 5 commands shipped together

Good fit It is for testing an allowance workflow, comparing dry-run and real-run results, checking execution records, and exporting a verified evidence bundle after a human provides consent.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/postoaklabs/ainumbers/air-gapped-helm-handover
Install

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.

Clone the repo
git clone --depth 1 https://github.com/PostOakLabs/ainumbers

Made for: Claude Code.

Or install ainumbers, the plugin that ships this one along with the rest of its 1 skill, 5 commands.

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 air-gapped-helm-handover

README.md
[![agentmods](https://agentmods.dev/badge/commands/postoaklabs/ainumbers/air-gapped-helm-handover/github.svg)](https://agentmods.dev/commands/postoaklabs/ainumbers/air-gapped-helm-handover)
Your own site
<a href="https://agentmods.dev/commands/postoaklabs/ainumbers/air-gapped-helm-handover"><img src="https://agentmods.dev/badge/commands/postoaklabs/ainumbers/air-gapped-helm-handover/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 air-gapped-helm-handover

Your own site · 80×15
<a href="https://agentmods.dev/commands/postoaklabs/ainumbers/air-gapped-helm-handover"><img src="https://agentmods.dev/badge/commands/postoaklabs/ainumbers/air-gapped-helm-handover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 442 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 $0.00032 $0.00442
Opus 5 $0.00016 $0.00221
Sonnet 5 $0.00006 $0.00088
Haiku 4.5 $0.00003 $0.00044

Measured 2d ago against content hash 4055d32f7a62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

air-gapped-helm-handover 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 2d 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.

agent-kit/claude-plugin/commands/air-gapped-helm-handover.md · 22 lines

What it actually says

Air-gapped control plane: the agent runs it, the human releases it, the bundle verifies without us

You are connected to a local Helm daemon at 127.0.0.1:4173. Run a CECL allowance workflow end to end, prove it, and get the evidence out the only way the daemon allows.

  1. Call catalog.search with "cecl". Pick the quarterly allowance pack. Call workflow.describe and workflow.manifest_get; list the nodes, the gates, and the manifest digest.
  2. Call workflow.dry_run on it (declare the io.modelcontextprotocol/tasks extension). Poll tasks/get until status is completed. Report the execution_hash.
  3. Call workflow.run on the same pack. Poll to completion. Report the execution_hash and whether it equals the dry run's.
  4. Call artifact.get and then artifact.verify on the real run. Report the per-step digests and the replay verdict.
  5. Attempt evidence.export with no ticket. Quote the error verbatim. Then tell me exactly what the human at the Helm UI has to do to mint a consent ticket, and wait for me to paste it.
  6. Once I paste the ticket, call evidence.export with it. Save the digest-level record.
  7. Cross-check the law: find the same kernel on mcp.ainumbers.co (find_tool "CECL allowance"), call it with the pack's sample inputs, and compare the kernel_digest and execution_hash to the Helm run. State whether the local daemon and the public worker agree.
  8. Call anchor_hash on the Helm run's execution_hash (Sigstore TSA). Return the receipt.
  9. Write the handover: what ran locally, what never left the machine, where the human consent sat in the flow, and how an auditor verifies the bundle offline with helmd verify <bundle> --keys <publicKeys.json> and no network.

Finish by stating the execution_hash you received and the ledger link a human can verify it at.

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. 2d ago First seen · 22 lines · 32 tokens per session scan A 4055d32f7a62

Subscribe to this mod's changes

air-gapped-helm-handover is a command published in the GitHub repository PostOakLabs/ainumbers (5 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 442 once invoked, about $0.0002 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 2026-09-06.