agentmods.dev

fluid-db: Instructions file for Codex

AGENTS.md

fluid-db AGENTS.md is an instructions file for Codex, OpenCode from TheMind-AI/fluid-db. It costs 2,253 tokens per session, scanned A, original, Apache-2.0.

A project instruction guide for the FluidDB codebase, including where its code and design documents live and how to check changes.

In plain words
What is it for?
It is for navigating the FluidDB repository, reading its linked design documents, running checks and tests, and working with its TypeScript and archived Python code.
Why use it?
It gives a coding agent the repository-specific rules and development commands it needs before changing the project.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is TheMind-AI/fluid-db's own configuration. It tells Codex and OpenCode how to work on fluid-db itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fluid-db configures →

not rated 113repo 16d ago A scan 2,253 tokens original Apache-2.0
View source ↗ TheMind-AI/fluid-db themind.ai
Reuse

Borrowing it

Nothing to install: this file belongs to TheMind-AI/fluid-db. 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/TheMind-AI/fluid-db/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/TheMind-AI/fluid-db

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.

agentmods badge for fluid-db AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/themind-ai/fluid-db/agents-md/github.svg)](https://agentmods.dev/instructions/themind-ai/fluid-db/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/themind-ai/fluid-db/agents-md"><img src="https://agentmods.dev/badge/instructions/themind-ai/fluid-db/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fluid-db AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/themind-ai/fluid-db/agents-md"><img src="https://agentmods.dev/badge/instructions/themind-ai/fluid-db/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,253 This file is loaded in full into every session.
When invoked 2,253 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02253 $0.02253
Opus 5.5 $0.00901 $0.00901
Sonnet 5.5 $0.00451 $0.00451
Haiku 4.5 $0.00225 $0.00225

Measured 18d ago against content hash 868d5fe04b09, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fluid-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 18d 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.

AGENTS.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

This project uses Linked Literate Programming (LLP) (upstream, v0.5.2). Design and research decisions live in numbered documents under llp/, and code points at them with @ref LLP NNNN#anchor — gloss comments. Start with LLP 0000.

Map

  • TypeScript is the primary implementation: packages/, evals/, examples/, scripts/ at the root.
  • Python is archived intact under deprecated/python/; run historical lab commands from that directory.
  • Start development with bun install --frozen-lockfile; verify with bun run check, bun run test:runtime, bun run verify:packages, and ./ref-check. bun run eval exercises TypeScript with free synthetic fixtures.
  • llp/0000 is the root: what FluidDB is, where things live, the constraints, and a table of every document.
  • llp/0015 describes the whole design as the evidence stands; read it before changing an architectural part.
  • Archived Python subsystems:
    • engine: 0004
    • write path: 0005
    • read path: 0006
    • background passes: 0007
    • Jev: 0008
    • evaluation: 0009
    • interfaces: 0010
    • the memory with several stores (deprecated/python/lab/memory/): 0013
  • Research:
    • how research is done: 0001
    • the findings ledger: 0002; round records 0002.000-0002.003 (rounds 1-4)
    • round 5: 0003 (RFC) and 0003.000 (results)
    • round 6: 0012 (RFC) and 0012.000 (results)
    • round 7: 0013 (RFC) and 0013.000 (results)
    • round 8: 0014 (RFC) and 0014.000 (results)
    • round 9: 0016 (RFC) and 0016.000 (results)
    • round 10, real conversations (private data under LAB_PRIVATE_DIR): 0017 (RFC) and 0017.000 (results)
    • round 11, other people's conversations (OpenAI only via LAB_PROCESSORS=openai): 0018 (RFC) and 0018.000 (results)
    • round 12, memory for conversation (meaning search, statements, a dossier): 0019 (RFC) and 0019.000 (results)
    • round 13, search and creation done properly, Jev picks (replay: deprecated/python/lab/bench/replay.py): 0020 (RFC) and 0020.000 (results)
    • round 14, a better picker, every wording kept, a live replay: 0021 (RFC) and 0021.000 (results)
    • round 15, the re-telling detector: 0022 (RFC) and 0022.000 (results)
    • SDK, database adapters, MCP and parity: 0023.001 and 0023.001.000
    • HiveNet feedback and portable memory skills: 0023.002 and 0023.002.000
    • Merge review, erasure generations and npm preview: 0023.003; release steps in docs/releasing.md.
    • the agenda: 0011
  • TypeScript conversation-memory package and Cloudflare service (packages/): 0023
  • BetterMind backend integration and memory-viewer assessment: 0023.000 (contracts, gaps and evaluation gates).
  • Sole-runtime BetterMind integration, SDK source/forget APIs and regression evidence: 0023.004.
  • Communication preferences, occasional check-ins, Jev boundary and technical feedback routing: 0023.005 (proposal).
  • TypeScript replay evaluation: 0024 (protocol), 0024.000 (verification), evals/README.md (commands).
  • Swappable SDK components and comparisons: 0024.001 (protocol), 0024.001.000 (real-provider results). bun run eval:compare is free; @fluiddb/fluiddb/eval exports the portable grader/comparison API.

Read the full file on GitHub · 131 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.

  1. 18d ago First seen · 131 lines · 2,253 tokens per session scan A 868d5fe04b09

Subscribe to this mod's changes

fluid-db AGENTS.md is an instructions file published in the GitHub repository TheMind-AI/fluid-db (113 stars, last pushed 16d ago), licensed Apache-2.0. It adds 2,253 tokens to every session, about $0.0090 per session on Opus 5.5. 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 2026-09-29.

Databasesaiai-agentsfluid-databaseretrieval-augmented-generationsemantic-search
Related

Other instructions, from other repositories

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 · 9,649 tokens

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 · 7,257 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,159 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens