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 skills add PostOakLabs/ainumbers --skill helm-bundle-to-policy-enginegit clone --depth 1 https://github.com/PostOakLabs/ainumbersWrote 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/skills/postoaklabs/ainumbers/helm-bundle-to-policy-engine)<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/helm-bundle-to-policy-engine"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/helm-bundle-to-policy-engine/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/skills/postoaklabs/ainumbers/helm-bundle-to-policy-engine"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/helm-bundle-to-policy-engine.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 | $0.00046 | $0.00540 |
| Opus 5.5 | $0.00018 | $0.00216 |
| Sonnet 5.5 | $0.00009 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
helm-bundle-to-policy-engine 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 15d 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
Helm bundle to policy engine
Export a Helm run as an in-toto statement and gate a deployment on it.
Prompt
Make a deployment gate read a Helm run's evidence instead of a human's thumbs-up.
- On your paired helmd, pick one completed workflow run. helmd artifact.get it; record the execution_hash and per-step digests.
- helmd artifact.verify the run against its manifest digest. A run that fails verify must never reach the gate; confirm your policy rejects it.
- helmd evidence.export the run as its in-toto statement export. Record the statement's subject digests.
- Inspect the statement: confirm the subjects name the artifacts your deployment actually consumes, not a superset.
- Negative test: modify one byte of a subject artifact and re-verify the statement; confirm verification fails. Quote the failure.
- Wire the gate: your policy engine (cosign verify or a Kyverno verify rule against the exported statement) checks the statement before allowing the deployment. Record the policy rule text.
- Give me the gate decision output for one allowed and one blocked deployment.
- Write the runbook entry for the platform channel: the export command, the policy rule, the two test outputs, and the line that the gate reads digests, not opinions. If a named tool is not in your tool list, call call_tool with { "name": "", "arguments": { … } }. It runs the same validation and returns the same receipt.
How to run
Connect an MCP-capable host to https://mcp.ainumbers.co/mcp, then give the prompt above to the assistant.
Use synthetic inputs only. Never paste personal or production data.
Verify what came back
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.
- 15d ago Changed 69447cd99f1e
- 19d ago First seen · 40 lines · 46 tokens per session scan A de5e18292804
helm-bundle-to-policy-engine is a skill published in the GitHub repository PostOakLabs/ainumbers (11 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 540 once invoked, about $0.0002 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 2026-09-27.
Other skills, from other repositories
implementing-aws-config-rules-for-compliance
Implementing AWS Config rules for continuous compliance monitoring of AWS resources, deploying managed and custom rules aligned to CIS and PCI DSS frameworks, configuring automatic remediation with SSM Automation, and aggregating compliance data across accounts.
hr-devops
Help HR managers, recruiters, and talent acquisition teams understand DevOps, Platform Engineering, Site Reliability Engineering (SRE), cloud infrastructure, CI/CD, and modern software delivery workflows. Use when asked to explain DevOps, screen DevOps candidates, understand CI/CD, compare DevOps and SRE, evaluate…
supply-chain-attack-response
Detect, respond to, and prevent software supply chain attacks on package registries, container images, and CI/CD pipelines with lockfile auditing, provenance verification, and emergency response playbooks.
llmops-platform-engineering
Build production LLMOps platforms with CI/CD, model promotion workflows, evaluation gates, rollback, and governance across cloud and self-hosted inference.
blue-green-deploy
Configure zero-downtime deployment strategies including blue-green, canary, and rolling deployments. Implement traffic shifting, health checks, and rollback procedures. Use when implementing production deployment strategies or zero-downtime releases.
aws-iam
Manage IAM users, roles, and policies. Implement least-privilege access and security best practices. Use when configuring AWS identity and access management.