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/themattberman/openclaw-100k-posts-kit/context-kernelnpx skills add TheMattBerman/openclaw-100k-posts-kit --skill context-kernelgit clone --depth 1 https://github.com/TheMattBerman/openclaw-100k-posts-kitWhat 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 | $0.00046 | $0.00707 |
| Opus 5 | $0.00023 | $0.00353 |
| Sonnet 5 | $0.00009 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
context-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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Kernel
This skill is the shared system layer for this repo.
It exists to keep the other skills aligned around one runtime contract:
- where shared files live
- which skill owns which files
- what can be overwritten vs appended
- how to pass context between skills without inventing missing state
Shared Workspace
All persistent state lives under ~/clawd/workspace/.
Brand Context
~/clawd/workspace/brand/voice-profile.md~/clawd/workspace/brand/notes.md
Research + Analysis
~/clawd/workspace/content-radar/config.yaml~/clawd/workspace/content-radar/briefings/~/clawd/workspace/content-dna/outputs/~/clawd/workspace/content-dna-batch/dna-cache/~/clawd/workspace/content-dna-batch/reports/
Production + Delivery
~/clawd/workspace/the-forge/outputs/~/clawd/workspace/monday-drop/outputs/
Ownership Rules
voice-labownsvoice-profile.md.voice-labmay append useful discoveries tonotes.md.content-radarowns briefing files incontent-radar/briefings/.content-dnaowns single-video analysis files.content-dna-batchowns pattern reports and DNA cache.the-forgeowns forged concept output.monday-dropowns delivery logs and exported run summaries.
Read Rules
voice-labmay read any file inworkspace/brand/.content-radarshould only readconfig.yaml.content-dnashould readvoice-profile.mdonly when adapting concepts.content-dna-batchshould read Content DNA outputs and its own cache.the-forgeshould readvoice-profile.md, pattern reports, and optionally the latest content-radar briefing.monday-dropshould read config, reports, and forged outputs. It should not invent missing brand state.
Write Rules
- Never overwrite
voice-profile.mdwithout showing the user what will change. notes.mdis append-only.- Dated run artifacts should create new files instead of overwriting old ones.
- If a script or skill cannot produce a promised artifact, say that clearly in the output instead of faking completeness.
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 · 81 lines · 46 tokens per session scan A ce4e20eb8341
context-kernel is a skill published in the GitHub repository TheMattBerman/openclaw-100k-posts-kit (20 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 707 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 2026-08-30.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…