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 instructions/mindburn-labs/helm-ai-kernel/agents-mdgit clone --depth 1 https://github.com/Mindburn-Labs/helm-ai-kernelWrote 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/instructions/mindburn-labs/helm-ai-kernel/agents-md)<a href="https://agentmods.dev/instructions/mindburn-labs/helm-ai-kernel/agents-md"><img src="https://agentmods.dev/badge/instructions/mindburn-labs/helm-ai-kernel/agents-md.svg" alt="Measured on agentmods" 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 | $0.00361 | $0.00361 |
| Opus 5 | $0.00180 | $0.00180 |
| Sonnet 5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
helm-ai-kernel AGENTS.md 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 4d 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
Agent Operational Guidelines for helm-ai-kernel
Welcome to the helm-ai-kernel repository. This is the core, open-source execution firewall daemon.
Developer Runbook
- Build daemon binary:
make build - Run comprehensive unit tests:
make test - Execute quality gates and linters:
make lint - Verify platform docs and fixture truth:
make test-platform - Verify conformance and use cases:
make crucible
Governance & Rules
- API and Protobuf mutations originate here and flow into the unified
contracts-catalog; do not invent contract truth in catalog mirrors. - Maintain strict zero-dependency boundaries on volatile commercial components.
- Every functional path must maintain green unit/integration tests and high coverage metrics.
- Treat RLM outputs as input evidence only. They become Kernel truth only when represented through existing verdict, receipt, ProofGraph, EvidencePack, contract, conformance, or verifier paths; do not add a separate RLM proof universe.
- Treat
mindburnlabsandpeycheff-comas Ivan's human GitHub accounts and preserve both as Mindburn-Labs organization owners/admins. Before any GitHub Actions state mutation, release/tag/package/artifact mutation, production promotion, or organization/repository access or settings mutation, read and follow/helm-privileged-ops; obtain exact single-use human approval and verify the authoritative readback. - Kernel owns verdict, permit, gateway, receipt, ProofGraph, EvidencePack, and
conformance semantics; it is not HELM's organization planner or business
runtime. OrgGenome/OrgPhenotype schemas and GeneratedSpec/evidence paths do
not make Kernel an
OrganizationRuntimeor prove a living company.
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.
- 4d ago First seen · 22 lines · 361 tokens per session scan A d61bd5bdb8f7
helm-ai-kernel AGENTS.md is an instructions file published in the GitHub repository Mindburn-Labs/helm-ai-kernel (55 stars, last pushed yesterday), licensed Apache-2.0. It adds 361 tokens to every session, about $0.0018 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 2026-08-30.
Other instructions, from other repositories
skilltotal CLAUDE.md
Claude Code instructions for pezhik/skilltotal, covering claude.md, project, commands, install (editable) + dev deps and run one test file / one test.
vellaveto CLAUDE.md
Claude Code instructions for paolovella/vellaveto, covering claude.md — vellaveto project instructions, mission, current 2026 execution priorities, before every session and architecture.
jakk CLAUDE.md
Claude Code instructions for akar5h/jakk, covering jakk — agent guidance, repo orientation, probe library policy (load-bearing), active project — fastmcp ecosystem audit and engineering conventions.
arcjet-js AGENTS.md
Instructions for arcjet/arcjet-js, covering agent guidance, examples live in arcjet/examples and integration work: review before a pr.
Agent-Security-Regression-Harness AGENTS.md
Instructions for OWASP/Agent-Security-Regression-Harness, covering ai agent guide: owasp agent security regression harness, project overview, architecture, contribution workflow and what needs doing.
tooltrust-scanner CLAUDE.md
Claude Code instructions for AgentSafe-AI/tooltrust-scanner: Use the /browse skill from gstack for all web browsing. Never use mcpclaude-in-chrome tools.