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/openshift-hyperfleet/kartograph/agents-mdgit clone --depth 1 https://github.com/openshift-hyperfleet/kartographWhat 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 | $0.01819 | $0.01819 |
| Opus 5 | $0.00910 | $0.00910 |
| Sonnet 5 | $0.00364 | $0.00364 |
| Haiku 4.5 | $0.00182 | $0.00182 |
Grade A, and why
kartograph 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 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
- Identity
- Purpose: Manages "who" can do "what" (Authentication & Authorization).
- Responsibilities:
- User, Team, and Tenant management.
- API Key lifecycle management.
- Management
- Purpose: The "Control Plane" for the platform. Manages metadata and configuration.
- Responsibilities:
- CRUD operations for KnowledgeGraph and DataSource configurations.
- Storing encrypted credentials (via Vault).
- Defining and managing synchronization schedules.
- Ingestion
- Purpose: Extracting raw data. This is where the Adapters (GitHub, K8s, etc.) live.
- Responsibilities:
- Running adapters to fetch "Raw Content Changesets" (what changed?).
- Generating sync manifests.
- Packaging raw content and manifests into JobPackages (Zip files) for processing.
- Extraction
- Purpose: Transforming raw content into Graph Data. This is where the AI Agent lives.
- Responsibilities:
- Processing JobPackages from Ingestion.
- Running the Claude Agent SDK to determine relationships and entities.
- Running the Deterministic Processor for non-AI tasks (renames/deletes).
- Producing a MutationLog (JSONL) of graph operations.
- Graph
- Purpose: The persistence engine. Executes writes and serves reads.
- Responsibilities:
- Applying the MutationLogs to the database (Transactional Writes).
- Managing database integrity (e.g., cascading deletes).
- Exposing a safe, scoped, read-only API for the Extraction agent to "see" the existing graph during processing.
- Querying
- Purpose: The consumer interface. Provides read access to end-users and agents.
- Responsibilities:
- Hosting the MCP (Model Context Protocol) Server.
- Translating user/agent questions into database queries.
- Enforcing rate limits and query complexity safety checks.
Logging should follow the Domain Oriented Observability pattern. Be sure to read the article to fully understand. Domain probes should be 100% preferred over logger.* and print().
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 · 202 lines · 1,819 tokens per session scan A 660be742a5e9
kartograph AGENTS.md is an instructions file published in the GitHub repository openshift-hyperfleet/kartograph (10 stars, last pushed 29d ago), licensed Apache-2.0. It adds 1,819 tokens to every session, about $0.0091 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.
Other instructions, from other repositories
knowledge-graph-system CLAUDE.md
Instructions for aaronsb/knowledge-graph-system, covering knowledge graph system - claude development guide, project overview, quick start, platform lifecycle and updates (pull images, no restart).
llm-wiki-agent GEMINI.md
Instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
obsidian-llm-wiki AGENTS.md
Instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.
remnic AGENTS.md
Instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
LeanKG AGENTS.md
Instructions for FreePeak/LeanKG, covering leankg — agent context, build & test, cli quick reference, mandatory: docker mcp project paths and tool discovery prefer-order.