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 instructions/orneryd/nornicdb/agents-mdgit clone --depth 1 https://github.com/orneryd/NornicDBWrote 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/instructions/orneryd/nornicdb/agents-md)<a href="https://agentmods.dev/instructions/orneryd/nornicdb/agents-md"><img src="https://agentmods.dev/badge/instructions/orneryd/nornicdb/agents-md.svg" alt="Measured on agentmods" 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 | $0.05957 | $0.05957 |
| Opus 5 | $0.02978 | $0.02978 |
| Sonnet 5 | $0.01191 | $0.01191 |
| Haiku 4.5 | $0.00596 | $0.00596 |
Grade A, and why
NornicDB AGENTS.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 5d 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 — 842 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NornicDB Development Guide for AI Agents
Version: 1.0.0
Last Updated: 2024-12-01
Target Audience: AI coding agents (Claude, GPT-4, etc.)
Core Philosophy
NornicDB is an enterprise-grade, high-performance graph database that prioritizes:
- Neo4j Compatibility - Drop-in replacement with zero code changes
- Performance - 3-52x faster than Neo4j across benchmarks
- Correctness - 90%+ test coverage, regression prevention mandatory
- Maintainability - Clean architecture, separation of concerns, DRY principles
- Documentation - Every public API fully documented with real-world examples
🎯 Golden Rules
1. Prove Value Before Merging
Every change must demonstrate measurable improvements without significant regressions:
- Performance: Benchmark before/after. Show ops/sec improvements.
- Memory: Profile memory usage. No >10% increases without justification.
- Code Quality: Maintain or improve test coverage (90% minimum).
- Compatibility: All Neo4j compatibility tests must pass.
Example:
// ❌ BAD: No proof of improvement
func optimizeQuery() { /* new algorithm */ }
// ✅ GOOD: Benchmarked and documented
// BenchmarkQueryOptimization shows 2.3x speedup:
// Before: 4,252 ops/sec
// After: 9,780 ops/sec
// Memory: -15% (reduced allocations)
func optimizeQuery() { /* new algorithm with proof */ }
2. Test-Driven Bug Fixes
MANDATORY WORKFLOW for all bugs:
- Write failing test - Reproduce the exact bug condition
- Verify test fails - Confirm it catches the bug
- Fix the bug - Implement minimal fix
- Verify test passes - Confirm fix works
- Add regression tests - Prevent future occurrences
Example from codebase:
// File: pkg/cypher/aggregation_bugs_test.go
// BUG #1: WHERE ... IS NOT NULL combined with WITH aggregation returns empty results
func TestBug_WhereIsNotNullWithAggregation(t *testing.T) {
// 1. Setup test data that triggers bug
setupAggregationTestData(t, store)
// 2. Execute query that fails in production
result, err := exec.Execute(ctx, `
MATCH (f:File)
WHERE f.extension IS NOT NULL
WITH f.extension as ext, COUNT(f) as count
RETURN ext, count
`, nil)
// 3. Assert expected behavior (this WILL fail before fix)
require.NoError(t, err)
assert.Equal(t, int64(2), extCounts[".ts"])
assert.Equal(t, int64(3), extCounts[".md"])
}
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.
- 5d ago First seen · 842 lines · 5,957 tokens per session scan A d99a2b788f94
NornicDB AGENTS.md is an instructions file published in the GitHub repository orneryd/NornicDB (852 stars, last pushed 6d ago), licensed MIT. It adds 5,957 tokens to every session, about $0.0298 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 instructions, from other repositories
payload AGENTS.md
AGENTS.md instructions for payloadcms/payload, a project described as: Payload is the open-source, fullstack Next.js framework, giving you instant backend superpowers. Get a full TypeScript backend and admin panel instantly. Use Payload as a headless CMS or for building powerful applications.
api-gateway CLAUDE.md
Claude Code instructions for membrane/api-gateway, covering claude.md, git & commit policy, working principles, 1. think before coding and 2. simplicity first.
fastify-boilerplate AGENTS.md
AGENTS.md instructions for marcoturi/fastify-boilerplate, covering agents.md, project overview, quick reference, architecture and layer boundaries (critical).
apollo-mcp-server AGENTS.md
AGENTS.md instructions for apollographql/apollo-mcp-server, covering claude.md, project overview, build & test commands, build and run all tests.
samyama-graph CLAUDE.md
Claude Code instructions for samyama-ai/samyama-graph, covering claude.md, project overview, build & development commands, build and run tests (1814 unit tests).
LAP CLAUDE.md
Claude Code instructions for Lap-Platform/LAP, covering lap - lean api platform, what this is, quick reference, install and run tests.