What is docgraph AGENTS.md?

A set of instructions for coding agents working on DocGraph, a local documentation server that builds a searchable knowledge graph from project documents. It covers project rules, commands, architecture, and required checks.

Use it to install, build, type-check, and test DocGraph, and to follow its clean-architecture and commit requirements.

It tells agents how the repository is organised and which checks must pass, reducing accidental rule violations and incomplete changes.

docgraph AGENTS.md — Instructions file by carrilloapps

Install

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.

agentmods

npx agentmods add instructions/carrilloapps/docgraph/agents-md

Clone the repo

git clone --depth 1 https://github.com/carrilloapps/docgraph

Made for: Codex, OpenCode.

Per session 828 This file is loaded in full into every session.

When invoked 828 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00828	$0.00828
Opus 5	$0.00414	$0.00414
Sonnet 5	$0.00166	$0.00166
Haiku 4.5	$0.00083	$0.00083

Measured yesterday against content hash 4c63ce71c11f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docgraph 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 yesterday.

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.

AGENTS.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents (Claude Code, opencode, and others) working in this repository. CLAUDE.md is a symlink to this file so every agent shares one source of truth.

Golden rule — commits

Never commit or push anything to git without co-authorship attribution. Every commit created with AI assistance MUST include a trailer identifying the assisting agent.

Do not use --no-verify, do not skip hooks, and do not force-push unless the maintainer explicitly asks. Only commit or push when the user requests it.

What this project is

DocGraph is a universal documentation knowledge-graph MCP server with hybrid full-text (SQLite FTS5) + vector search. It ships a CLI and an MCP server and is designed to run as a local MCP server inside a repository.

Commands

npm install        # install dependencies
npm run build      # compile TypeScript to dist/
npm run typecheck  # type-check without emitting
npm test           # compile tests (tsconfig.test.json) and run node:test

Always run npm run typecheck and npm test before proposing a commit.

Architecture (Clean Architecture)

Dependencies point inward. Never let an inner layer import an outer one.

src/domain/ — entities, ports (interfaces), pure services. Depends on nothing.
src/application/ — use cases (IndexingService, SearchService, QueryService). Depends only on domain.
src/infrastructure/ — adapters implementing domain ports (SQLite, embeddings, filesystem, config). Depends on domain.
src/presentation/ — entry points (CLI, MCP server).
src/container.ts — the composition root; the only place that instantiates concrete adapters. Wire new dependencies here.

When adding a feature: define/extend a port in domain, implement the adapter in infrastructure, orchestrate it in an application service, and wire it in container.ts.

Cross-platform & path rules

This tool must run on any OS and is meant to be embedded as a local MCP server.

Read the full file on GitHub · 82 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.

yesterday First seen · 82 lines · 828 tokens per session scan A 4c63ce71c11f

Subscribe to this mod's changes

docgraph AGENTS.md is an instructions file published in the GitHub repository carrilloapps/docgraph (0 stars, last pushed 1mo ago), licensed MIT. It adds 828 tokens to every session, about $0.0041 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.

Git and workflow Testing Writing and docs ai-agents claude cli documentation embeddings full-text-search

docgraph AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Golden rule — commits

What this project is

Commands

Architecture (Clean Architecture)

Cross-platform & path rules

What this file has done since we first saw it

Other instructions, from other repositories

knowledge-base CLAUDE.md

mcp-plesk-dev-docs copilot-instructions.md

local-RAG-backend CLAUDE.md

esp32-docs-mcp CLAUDE.md

inkdex AGENTS.md

self-doc AGENTS.md