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/kruschdev/krusch-context-mcp/agents-mdgit clone --depth 1 https://github.com/kruschdev/krusch-context-mcpWrote 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/kruschdev/krusch-context-mcp/agents-md)<a href="https://agentmods.dev/instructions/kruschdev/krusch-context-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kruschdev/krusch-context-mcp/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 | $0.03347 | $0.03347 |
| Opus 5 | $0.01673 | $0.01673 |
| Sonnet 5 | $0.00669 | $0.00669 |
| Haiku 4.5 | $0.00335 | $0.00335 |
Grade A, and why
krusch-context-mcp 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 4d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
krusch-context-mcp — Agent Context
Unified MCP server: PG-Git codebase search + Homelab episodic memory + Holographic Nuggets + External docs search.
Last audit: 2026-07-28 | Version: 1.3.0 | Tools: 44
Architecture Overview
This project is a single MCP server (stdio transport) that unifies three subsystems into one process:
- Episodic Memory — Vector-embedded memories (
bugs,lessons,priorities,outcomes,activity) stored in hybrid SQLite + Postgres. These maintain agent state across sessions, track workarounds, and document learnings. For a comprehensive guide, see EPISODIC_MEMORY.md. - Holographic Nuggets — Lightweight key-value steering facts (preferences, conventions, corrections) with semantic retrieval
- Codebase Search — Semantic search over all indexed source files via the sibling
pg-gitproject - Proactive Auditor (Memory Agent Loop) — Background trajectory auditor that verifies actions against past rules and updates weights based on developer feedback loops (Direct-OPD/PUST)
- pgContext Vector Acceleration — Optional native PostgreSQL 17 engine extension providing page-native HNSW indexes (
pgcontext_hnsw) and single-pass JSON metadata filtering with exact MVCC/RLS re-checking. - Agentic Context Management (ACM) — Context fragment lifecycle staging, compaction, eviction retention policies, and context window token budget auditing (HF Paper ArXiv: 2607.21503).
All six share a single pg.Pool connection to kruschdb and a single fleet-balanced Ollama embedding pipeline.
Lakebase Architecture (Compute/Storage Decoupling)
Project-scoped data follows a two-tier model:
- Compute Cache: Per-project SQLite databases at
<project>/.agent/memory.db— zero-latency reads - Object Storage: Durable Postgres tables (
ide_agent_memory,ide_agent_nuggets,interaction_memory,ide_agent_context_lifecycle) — fleet-wide persistence - Sync: Async write-behind (SQLite → Postgres) on every write; read-ahead pull (Postgres → SQLite) on first project access
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.
- 4d ago First seen · 183 lines · 3,347 tokens per session scan A 767b25f8aa32
krusch-context-mcp AGENTS.md is an instructions file published in the GitHub repository kruschdev/krusch-context-mcp (71 stars, last pushed 1mo ago), licensed MIT. It adds 3,347 tokens to every session, about $0.0167 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
cognirepo CLAUDE.md
Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).
openexp CLAUDE.md
Instructions for anthroos/openexp, covering openexp — development instructions, memory protocol (mandatory), before starting any task, after completing a task and when the user shares context.