What is open-zk-kb AGENTS.md?

Development instructions for open-zk-kb, a TypeScript and Bun knowledge base that stores persistent agent memory in Markdown files and a SQLite full-text search index. It explains its commands, tests, structure, and agent-related files.

Use them when changing storage, search, MCP server behaviour, agent instructions, tests, or the build and evaluation process.

They show how to build, test, lint, and evaluate the knowledge base without breaking its memory and search behaviour.

How mrosnerr/open-zk-kb configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to mrosnerr/open-zk-kb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mrosnerr/open-zk-kb/dev/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/mrosnerr/open-zk-kb

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mrosnerr/open-zk-kb/agents-md.svg)](https://agentmods.dev/instructions/mrosnerr/open-zk-kb/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/mrosnerr/open-zk-kb/agents-md"><img src="https://agentmods.dev/badge/instructions/mrosnerr/open-zk-kb/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,847 This file is loaded in full into every session.

When invoked 3,847 The same file — it is already loaded in full.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.03847	$0.03847
Opus 5	$0.01924	$0.01924
Sonnet 5	$0.00769	$0.00769
Haiku 4.5	$0.00385	$0.00385

Measured 8d ago against content hash 7b636dbfbb98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

open-zk-kb AGENTS.md scanned grade C with 1 finding 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 8d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf dist/ && bun run build # Clean rebuild

AGENTS.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

open-zk-kb — Agent Knowledge Base

Overview

Persistent memory for agents. One knowledge base for all your tools — so context persists across sessions and clients. TypeScript/Bun, SQLite FTS5, Markdown files with YAML frontmatter. Entry point: mcp-server.ts (MCP stdio). See BRAND.md for public voice and positioning.

Commands

bun run build              # Compile TS → dist/ (REQUIRED after every change)
bun test                   # Run all tests
bun test --watch           # Watch mode
bun test --coverage        # Coverage report
bun run lint               # ESLint check
bun run lint:fix           # Auto-fix lint
rm -rf dist/ && bun run build  # Clean rebuild
EVAL=1 bun test tests/eval/eval.test.ts --timeout 120000  # Agent eval suite

Testing

Six-areas template per https://github.blog/ai-and-ml/github-copilot/how-to-write-a-great-agents-md-lessons-from-over-2500-repositories/

Framework: bun:test with custom harness (tests/harness.ts) and fixtures
Run all: bun test; pre-commit also runs bun run typecheck
Coverage: bun test --coverage
Eval suite: EVAL=1 bun test tests/eval/eval.test.ts --timeout 120000 (agent-quality regression tests)
CI: .github/workflows/ci.yml runs Bun build + lint + test + coverage on every PR
Conventions: tests use createTestHarness() / cleanupTestHarness(); never use .skip without justification; mock OS-level interactions, never real side effects

Structure

.
├── src/                   # Source (see src/AGENTS.md)
│   ├── mcp-server.ts      # MCP stdio server entry
│   ├── tool-handlers.ts   # Shared handler functions
│   ├── storage/            # NoteRepository — SQLite+FTS5+filesystem
│   │   ├── IndexBuilder.ts # Auto-generates per-project index notes
│   │   └── LogAppender.ts  # Auto-appends to per-project log notes
│   ├── obsidian.ts         # Obsidian detection, vault registry, launch
│   └── utils/              # Path resolution, wikilink parsing
├── skill-templates/       # Skill templates for Claude Code
│   └── open-zk-kb/        # Copied to ~/.claude/skills/open-zk-kb/ on install
│       ├── SKILL.md        # Main skill (frontmatter + instructions)
│       └── kinds-reference.md  # Supporting reference (loaded on-demand)
├── tests/                 # Test suite (see tests/AGENTS.md)
├── docs/                  # User-facing documentation
│   ├── architecture.md    # System design, dual storage, design decisions
│   ├── configuration.md   # Full config reference (single YAML file)
│   ├── note-lifecycle.md  # Note statuses, kinds, review system
│   ├── development.md     # Local dev workflow, testing, debugging
│   └── setup-guide.md     # Step-by-step install for all clients
├── scripts/               # rebuild-db.ts
├── dist/                  # Compiled output (tsc) — this is what runs
└── .gitignore             # Excludes dist/, node_modules/, config.yaml, etc.

Read the full file on GitHub · 216 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.

8d ago First seen · 216 lines · 3,847 tokens per session scan C 7b636dbfbb98

Subscribe to this mod's changes

open-zk-kb AGENTS.md is an instructions file published in the GitHub repository mrosnerr/open-zk-kb (7 stars, last pushed 10d ago), licensed MIT. It adds 3,847 tokens to every session, about $0.0192 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Memory and context ai-coding-assistant ai-memory knowledge-management mcp mcp-server

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

open-zk-kb: Instructions file for Codex