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/platano78/faulkner-db/agents-mdgit clone --depth 1 https://github.com/Platano78/faulkner-dbWrote 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/platano78/faulkner-db/agents-md)<a href="https://agentmods.dev/instructions/platano78/faulkner-db/agents-md"><img src="https://agentmods.dev/badge/instructions/platano78/faulkner-db/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 5.1 | $0.01249 | $0.01249 |
| Opus 5 | $0.00624 | $0.00624 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
faulkner-db 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Faulkner DB — AGENTS.md (router / the map)
You are the generic agent. Reading this makes you the Faulkner DB agent. On entry: read this map → route to the area for the task → load ONLY that area's Inputs.
What this is
A temporal knowledge-graph "architectural memory" system exposed as an MCP server: stores
Decisions / Patterns / Failures in a graph, does hybrid (graph + vector) search, and runs
NetworkX structural analysis (gaps, bridges, communities). Python 3.9–3.12, runs as Docker
containers (FalkorDB + Postgres + ChromaDB) on host ai-utility. The live server is
mcp_server/server_fastmcp.py (FastMCP, registers all 13 tools). A legacy stdio path
(mcp_server/server.py + mcp_server/mcp_tools.py, 7-tool subset) coexists — not the live path.
Areas (route by task — load Inputs, skip the rest)
| If the task is about… | Read (Inputs) | Skip |
|---|---|---|
| MCP tools / server behaviour (add_decision, query_decisions, add_pattern, add_failure, find_related, detect_gaps, get_timeline, find_knowledge_gaps, find_influential_patterns, find_knowledge_communities, find_bridge_patterns, get_graph_summary, query_patterns_semantic) | mcp_server/server_fastmcp.py (live; thin tool wrappers that delegate to →) mcp_server/mcp_tools.py (shared tool impls + input validation), common/schemas.py (input models: DecisionInput/PatternInput/FailureInput), core/knowledge_types.py (storage models Decision/Pattern/Failure — also validate on construct), mcp_server/utils.py |
legacy mcp_server/server.py (stdio entrypoint), unused dup mcp_server/schemas.py, root archival *.md |
| Legacy stdio entrypoint (only when explicitly asked) | mcp_server/server.py, mcp_server/mcp_tools.py (TOOL_REGISTRY) |
the FastMCP server |
| Graph store / client + data models (FalkorDB adapter) | core/graphiti_client.py (FalkorDBAdapter, GraphitiClient, MetricsCollector), core/knowledge_types.py (Decision/Pattern/Failure), core/config_loader.py |
data/ contents |
| Hybrid search (graph+vector fusion, reranking) | core/hybrid_search.py (reciprocal_rank_fusion, crossencoder_reranker, query_decomposer, extract_temporal) |
data/embeddings/, data/chroma/ contents |
| Structural graph analysis (gaps/bridges/communities/influence) | core/gap_detector.py (GapDetector, GapType, Severity, GapReport), mcp_server/networkx_analyzer.py |
search/storage dirs |
| Ingestion / bulk import (agent-genesis, chromadb extraction) | ingestion/ (agent_genesis_*.py, chromadb extractor scripts), mcp_server/ingestion_guards.py |
ingestion/*.log, ingestion/*_checkpoint.json |
| Deploy / Docker / infra | docker/docker-compose.yml, docker/Dockerfile, docker/redis.conf, config/graphiti_config.yaml, config/mcp_config.json |
docker/data/, docker/backups/, source dirs |
| Ops / health / migrations / sync | scripts/ (health_check.py, backup-faulkner.sh, migrate_*.py, faulkner-health-graph.{service,timer}) |
logs/ |
| Tests | tests/, comprehensive_mcp_test.py (root) |
source dirs unless tracing a failure |
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 · 44 lines · 1,249 tokens per session scan A 4451c4dea6a4
faulkner-db AGENTS.md is an instructions file published in the GitHub repository Platano78/faulkner-db (3 stars, last pushed 17d ago), licensed MIT. It adds 1,249 tokens to every session, about $0.0062 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
synaptic-memory CLAUDE.md
Claude Code instructions for PlateerLab/synaptic-memory, covering synaptic memory — 프로젝트 지침, 프로젝트 개요, 핵심 원칙, easy api and 2줄로 시작.
automem CLAUDE.md
Instructions for verygoodplugins/automem, covering claude.md, project overview, development commands, setup environment and development.
memora CLAUDE.md
Claude Code instructions for agentic-box/memora, covering memora and memory.
neurostack CLAUDE.md
Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.
Dragon-Brain CLAUDE.md
Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.
mcp-automem AGENTS.md
AGENTS.md instructions for verygoodplugins/mcp-automem, covering agents.md, project overview, build & development, build typescript to dist/ and development with hot-reload.