What is context-kernel CLAUDE.md?

A set of Claude Code instructions for the context-kernel project, a self-hosted memory service that agents read through an MCP server. It defines project rules, security boundaries, and development conventions.

Use it when working on context-kernel so the agent knows its architecture, allowed operations, secrets policy, and standard commands.

It keeps agent changes aligned with the project's data-protection rules, such as separating read and write access and keeping private content out of commits.

context-kernel CLAUDE.md — Instructions file by dkritarth

Install

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.

agentmods

npx agentmods add instructions/dkritarth/context-kernel/claude-md

Clone the repo

git clone --depth 1 https://github.com/dkritarth/context-kernel

Per session 638 This file is loaded in full into every session.

When invoked 638 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00638	$0.00638
Opus 5	$0.00319	$0.00319
Sonnet 5	$0.00128	$0.00128
Haiku 4.5	$0.00064	$0.00064

Measured yesterday against content hash b7c6fddb268b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-kernel CLAUDE.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 yesterday.

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.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md: context-kernel

Working conventions for any Claude Code session in this repo.

What this project is

A personal, self-hostable context memory for LLMs. Hand-curated Markdown is the source of truth; a Cloudflare Worker serves it as a remote MCP server; agents extend it only through an append-only journal that a human promotes by hand. Not a website, not a public API, no UI.

Hard rules (never violate)

content/ is sacred and gitignored. It holds the owner's real curated context. Never commit it. Never let an automated process edit it. Only content.example/ (fake templates) is committed.
No curated-write tool. MCP exposes read tools + an append-only append_journal. Nothing an agent can call may modify curated context. Promotion is a local, human-run script.
Two tokens, two scopes. READ_TOKEN serves context; WRITE_TOKEN gates journal writes. Read token must never reach write tools. Use constant-time token comparison.
Secrets stay in Cloudflare. Never hardcode tokens or KV namespace IDs. wrangler.toml (real) and .dev.vars are gitignored; only wrangler.toml.example is committed.
No personal data in URLs, query strings, logs, or cache keys.
Verify moving APIs against live docs. MCP transport and Cloudflare remote-MCP + Claude connector auth change often. Confirm current shape before implementing; do not guess an API.

Stack

Runtime: Cloudflare Workers (V8 isolate). Keep deps minimal.
Storage: Cloudflare KV.
Language: TypeScript.
Protocol: remote MCP over HTTP, dual auth (plain bearer + OAuth via @cloudflare/workers-oauth-provider), both converging on /mcp. See src/worker.ts and src/mcp/oauth.ts for the routing and scope model.

Commands

npm run typecheck
npm test
npm run build      # content/*.md -> artifacts/kv-bulk.json + meta.json
npm run dev        # wrangler dev, reads .dev.vars
npm run promote    # review journal:* entries; never auto-edits content/

Read the full file on GitHub · 60 lines

Changes

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.

yesterday First seen · 60 lines · 638 tokens per session scan A b7c6fddb268b

Subscribe to this mod's changes

context-kernel CLAUDE.md is an instructions file published in the GitHub repository dkritarth/context-kernel (1 stars, last pushed 1mo ago), licensed MIT. It adds 638 tokens to every session, about $0.0032 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.

DevOps and cloud Memory and context Security ai-agents claude cloudflare-kv cloudflare-workers context-management llm-memory

context-kernel CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md: context-kernel

What this project is

Hard rules (never violate)

Stack

Commands

What this file has done since we first saw it

Other instructions, from other repositories

supermemory CLAUDE.md

Tianshu-harness CLAUDE.md

flarestarter CLAUDE.md

baerly-storage CLAUDE.md

Waggle-mcp AGENTS.md

hqbase AGENTS.md