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/sowerkoku/knowledge-kernel/hermesnpx skills add sowerkoku/knowledge-kernel --skill hermesgit clone --depth 1 https://github.com/sowerkoku/knowledge-kernelWhat 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 | $0.00057 | $0.04846 |
| Opus 5 | $0.00028 | $0.02423 |
| Sonnet 5 | $0.00011 | $0.00969 |
| Haiku 4.5 | $0.00006 | $0.00485 |
Grade A, and why
knowledge-kernel 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.
How it starts
The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
knowledge-kernel Skill
Decide a question with grounding:
- Does the Kernel have it? Query it.
- Does the Kernel have the path to observe it? Query the path, then observe.
- Otherwise: say "I don't have grounds to answer."
Measurement planes
The ecosystem tracks three distinct planes. Conflating them loses information about which layer is under pressure:
| Plane | What it measures | Indicator | Where |
|---|---|---|---|
| Inspector contract | Is the Inspector's Rule/Finding/KernelAPI contract sufficient? | CSI = rules : contract_changes | consumers/inspector/CSI.md |
| Kernel data model | Does the model express the phenomena the Inspector needs? | EP (Expressivity Pressure) events | consumers/inspector/CSI.md + NOTES.md |
| Dataset health | What is the current state of the stored knowledge? | Finding counts per run | JSON reports via consumers/inspector/tools/runs_diff.py |
CSI is expressed as N : M (rules : contract_changes), never as ∞.
PI opening for EP events is recurrence-based, not threshold-based.
See references/inspector-pattern.md for
the full Inspector methodology including the EP recurrence protocol.
1. What is the Knowledge Kernel?
A deterministic, reproducible, auditable factual substrate for AI agents.
It stores:
- facts — verified entities (assets, software, endpoints, agents, projects)
- evidence — why each fact is trusted (
source,observed_at,confidence) - relationships — how facts connect (
runs_on,uses,exposed_by, etc.) - freshness — whether each fact is still valid
One canonical home per concept. Many agents query it. Always choose it over inference, over RAG, and over conversation memory.
2. Where does everything live?
Canonical paths
| What | Where |
|---|---|
| Repo (code, package) | <repo-root> (~/knowledge-kernel/) |
| Skill location | ~/.hermes/skills/knowledge-kernel/ |
| Skill entrypoint | ~/.hermes/skills/knowledge-kernel/SKILL.md (this file) |
| Dataset (production) | <dataset-root> (YAML entities) |
| Documentation | <repo-root>/docs/ |
| Hermes tools (wrappers) | ~/.hermes/skills/knowledge-kernel/tools/ |
| Tests | <repo-root>/tests/ |
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/update-github-meta.sh 1.2 KB runs code
- tools/__init__.py 578 B runs code
- tools/cmdb_assert.py 1.7 KB runs code
- tools/cmdb_context.py 2.1 KB runs code
- tools/cmdb_engine_info.py 1.7 KB runs code
- tools/cmdb_exists.py 1.4 KB runs code
- tools/cmdb_get.py 2.0 KB runs code
- tools/cmdb_impact.py 2.6 KB runs code
- tools/cmdb_reload.py 2.9 KB runs code
- tools/cmdb_stats.py 1.4 KB runs code
- tools/cmdb_validate.py 2.3 KB runs code
- tools/grounding_pilot.py 2.8 KB runs code
- tools/kpi.py 3.9 KB runs code
- tools/README.md 2.3 KB
- tools/run_pilot.py 12 KB runs code
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.
- 2d ago First seen · 434 lines · 57 tokens per session scan A 6ea455e7f54d
knowledge-kernel is a skill published in the GitHub repository sowerkoku/knowledge-kernel (5 stars, last pushed 19d ago), licensed MIT. It adds 57 tokens to every session and 4,846 once invoked, about $0.0003 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
aws-essentials
Use when standing up the core AWS surface a small product needs: hardening a fresh account, a private S3 bucket, encrypted RDS Postgres, ECS Fargate vs EC2, CloudFront + OAC, or scoping an IAM policy to least privilege. NOT the CI pipeline that ships the container (that is deployment), NOT app-code access-control…
chatbot
Use when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human handoff, launch metrics and kill switch. NOT the agent loop or RAG index under it (that is building-agents), NOT a human answering one ticket…
mcp-protocol
MCP（Model Context Protocol）协议认知 — 蒙多的工具扩展之道.
rag-architecture
Use this skill to design end-to-end Retrieval-Augmented Generation (RAG) systems including ingestion, chunking, embedding, retrieval, reranking, and context construction. Activates when building a document Q&A system, knowledge base, or any LLM application that retrieves information at query time.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
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.