What is docsmint AGENTS.md?

Project instructions and technical reference notes for DocsMint, a self-hosted workspace for creating and managing documents and knowledge. They describe its APIs, web app, editor, database, storage, and development conventions.

Guiding work on DocsMint’s backend, frontend, editor, authentication, database, storage, and documentation. They also record required runtime and package conventions.

They give coding agents the project-specific rules and technology choices needed to make compatible changes.

How HiAi-gg/docsmint configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to HiAi-gg/docsmint. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/HiAi-gg/docsmint/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/HiAi-gg/docsmint

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hiai-gg/docsmint/agents-md.svg)](https://agentmods.dev/instructions/hiai-gg/docsmint/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hiai-gg/docsmint/agents-md"><img src="https://agentmods.dev/badge/instructions/hiai-gg/docsmint/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 6,159 This file is loaded in full into every session.

When invoked 6,159 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.06159	$0.06159
Opus 5	$0.03080	$0.03080
Sonnet 5	$0.01232	$0.01232
Haiku 4.5	$0.00616	$0.00616

Measured 2d ago against content hash 7697a6df7d01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

docsmint AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsS http://localhost:50700/api/health

AGENTS.md · 426 lines

How it starts

The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DocsMint — AGENTS.md

Role: Standalone, self-hosted AI-native knowledge workspace with public REST, SDK, CLI, MCP, PWA, and host-extension contracts. Structured TipTap JSON is canonical; Markdown is the import, export, and source-editing format. Status: ready Project documentation lives in README.md, docs/, and AGENTS.md.

Cheat-sheet — Conventions

Runtime: Bun 1.3.14+ (no Node, no npm, no yarn)
Backend: Elysia 1.4.28+ (ESM-only, TypeScript strict)
Frontend: SvelteKit 2.60+ + Svelte 5.55+ (runes: true)
UI: @hiai-gg/hiai-ui + shadcn-svelte 1.2.7+ (new-york style) + Tailwind CSS v4
Editor: svelte-tiptap + TipTap v3 (WYSIWYG + raw MD toggle)
ORM: Drizzle ORM 0.45.2+
Auth: Better Auth
Validation: Zod (every route validated)
DB: PostgreSQL 18.1 + pgvector (personal owner_id plus optional external workspace_id)
Vector index (optional): pgvectorscale StreamingDiskANN with SbqCompression, loaded in the unified PostgreSQL image (see postgres/Dockerfile)
Cache: Redis 8 (the reference image tracks redis:8-alpine)
Storage: SeaweedFS (S3-compatible)
Embeddings: external embedding API (configurable) + optional self-hosted Ollama; every provider result must be a finite, non-zero 1024-dimensional vector
Search: exact/title, multilingual lexical, fuzzy, vector, adaptive expansion, GraphRAG, and cross-encoder rerank after RRF (default on; SEARCH_RERANK_ENABLED=false restores RRF-only)
GraphRAG: automatic LLM entity extraction + AGE graph expansion in normal search; the operator flag remains a kill switch for degraded deployments
Re-embed invariant: metadata mutations (tag / folder / category rename and delete) MUST trigger re-embed via backend/src/lib/reembed.ts.
Logging: Pino
Lint: Biome 2.5+ (bun run lint)
Tests: Vitest (bun test --path-ignore-patterns="*node_modules*")
Structure: backend/src/ (api/, embedding/, lib/) + frontend/ (SvelteKit) + packages/db/ (Drizzle)
Module boundaries: api/ MUST NOT export internal functions · embedding/ MUST NOT import from api/ · lib/ MUST NOT import from api/ or embedding/
Env access: ONLY via src/lib/config.ts (Zod); every CORS_ORIGINS, EMBEDDING_*, GRAPH_*, SEARCH_*, HYBRID_*, CHUNK_*, *_REEMBED_BATCH_SIZE through .env
Token import: @hiai-gg/hiai-ui/styles/tokens.css
Ports: API 50700 · frontend dev 50701 · Postgres 5437 · Redis 6384 · SeaweedFS 50702/50703 · Caddy 80/443
No Playwright — use agent-browser for E2E
English only in code, comments, docs, README, AGENTS.md (zero Cyrillic)

Read the full file on GitHub · 426 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.

2d ago Changed · +4 lines · +272 tokens per session 7697a6df7d01
7d ago First seen · 422 lines · 5,887 tokens per session scan A 37ce03f778d5

Subscribe to this mod's changes

docsmint AGENTS.md is an instructions file published in the GitHub repository HiAi-gg/docsmint (58 stars, last pushed yesterday), licensed Apache-2.0. It adds 6,159 tokens to every session, about $0.0308 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Documents ai-agents graphrag knowledge-management mcp progressive-web-app pwa

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

docsmint: Instructions file for Codex