OpenShelf AGENTS.md

Repository instructions for OpenShelf, a project that manages searchable knowledge bases built from document collections. They describe how agents should search those collections and cite retrieved evidence.

In plain words
What is it for?
Use them when answering questions from PDF collections, choosing among multiple knowledge databases, following citation rules, and handling missing evidence.
Why use it?
They help keep answers grounded in the project’s documents and prevent agents from bypassing the supported knowledge-base tools.

Instructions file for CodexOpenCode

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/vecbase-labs/openshelf/agents-md
Clone the repo
git clone --depth 1 https://github.com/vecbase-labs/OpenShelf

Made for: Codex, OpenCode.

Per session 523 This file is loaded in full into every session.
When invoked 523 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.

ModelPer sessionOnce invoked
Fable 5 $0.00523 $0.00523
Opus 5 $0.00262 $0.00262
Sonnet 5 $0.00105 $0.00105
Haiku 4.5 $0.00052 $0.00052

Measured 2d ago against content hash af090c96d662, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

OpenShelf 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 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.

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 · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Agent Guidelines

Use the repository's MCP tools and public APIs when working with the knowledge base. Do not bypass the server by reading DuckDB files, generated indexes, or cached artifacts directly unless the task is explicitly to debug storage internals.

Knowledge Base Policy

When a user asks a question that should be grounded in an existing PDF corpus, search the configured knowledge base first. Treat retrieved evidence as the source of truth and cite the returned document, page, chunk, or evidence item in answers.

If direct evidence is not found, say so plainly. Only use independent reasoning when the user allows it or when the selected database profile permits labeled independent reasoning. Keep independent reasoning clearly separated from knowledge-base evidence.

Multiple Knowledge Databases

This project can manage multiple physical DuckDB knowledge bases with a single MCP server. Different corpora are selected by db_name; openshelf is the MCP server name and must not be used as a database name.

General workflow:

  1. If the user has not specified a database and multiple databases exist, call list_db and ask which db_name to use.
  2. If the user specifies a database for the current session, call set_active_db.
  3. Do not search across databases unless the user explicitly asks for cross-database search.
  4. When searching multiple databases, report each database's evidence and answerability status separately.
  5. If a tool returns status: "db_selection_required", stop and ask the user to choose a database.

Answering Rules

  1. Answer from the knowledge base only when answerability.status is supported or the tool explicitly returns direct evidence.
  2. Cite returned evidence locations; do not present weakly related material as direct support.
  3. If the status is related_only, explain that the corpus contains only weakly related material and ask whether to proceed with independent reasoning.
  4. If the status is not_found, explain that no usable evidence was found and ask whether to proceed independently.
  5. When independent reasoning is used, label it as independent reasoning and do not imply it came from the corpus.

Read the full file on GitHub · 36 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. 2d ago First seen · 36 lines · 523 tokens per session scan A af090c96d662

Subscribe to this mod's changes

OpenShelf AGENTS.md is an instructions file published in the GitHub repository vecbase-labs/OpenShelf (3 stars, last pushed 1mo ago), licensed MIT. It adds 523 tokens to every session, about $0.0026 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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

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

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 · 4,345 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js 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