Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sowerkoku/knowledge-kernelnpx agentmods add skills/sowerkoku/knowledge-kernel/hermesWrote 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/sowerkoku/knowledge-kernel/hermes)<a href="https://agentmods.dev/skills/sowerkoku/knowledge-kernel/hermes"><img src="https://agentmods.dev/badge/skills/sowerkoku/knowledge-kernel/hermes/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/sowerkoku/knowledge-kernel/hermes"><img src="https://agentmods.dev/badge/skills/sowerkoku/knowledge-kernel/hermes.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 | $0.00057 | $0.04846 |
| Opus 5.5 | $0.00023 | $0.01938 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 2mo ago), licensed MIT. It adds 57 tokens to every session and 4,846 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 2026-08-31.
Other skills, from other repositories
awm-rsi-toolkit
Run AWM (Agent Workflow Memory, Wang et al. 2024) on an agent - induce reusable workflows from its successful trajectories, online over a training stream or offline from supplied experiences, then freeze the workflow memory and measure it on a published Benchmark.
computer-history
Answer questions about what the user recently did on their computer — who contacted them, what they were working on, where they left off — by reading the local Computer History summaries and raw event streams.
docx
Create, read, edit, review, redline, comment on, merge, audit, render, and verify .docx Word documents, including layout-sensitive and OOXML-level work.
update-setup
A one-time setup wizard for creating a personalised upgrade guide for a workspace. It checks for an existing guide, identifies the current version and installation clues, and requires confirmation of the installation method before writing a new guide.
skill-creator
Create, edit, improve, tidy, review, audit, or restructure memmy-agent skills and SKILL.md files.
memmy-memory
Use the shared Memmy memory service to retrieve relevant prior context and persist durable Agent turns, facts, decisions, preferences, procedures, and follow-ups.