What is zvec-tool AGENTS.md?

A command-line tool for searching project documents by meaning rather than only by matching words. It turns selected files, such as Markdown notes or regulations, into a local searchable database.

It helps index a chosen documentation folder and search it in English or Russian, returning file paths, relevance scores, and short previews; source code and configuration files should instead be searched with grep.

It helps an AI assistant find relevant background when the user's question uses different words from the source document.

How alexqem/zvec-tool configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to alexqem/zvec-tool. 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/alexqem/zvec-tool/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/alexqem/zvec-tool

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/alexqem/zvec-tool/agents-md/github.svg)](https://agentmods.dev/instructions/alexqem/zvec-tool/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/alexqem/zvec-tool/agents-md"><img src="https://agentmods.dev/badge/instructions/alexqem/zvec-tool/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/alexqem/zvec-tool/agents-md"><img src="https://agentmods.dev/badge/instructions/alexqem/zvec-tool/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,439 This file is loaded in full into every session.

When invoked 1,439 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.

Model	Per session	Once invoked
Fable 5.1	$0.01439	$0.01439
Opus 5.5	$0.00576	$0.00576
Sonnet 5.5	$0.00288	$0.00288
Haiku 4.5	$0.00144	$0.00144

Measured 2mo ago against content hash 0c7826a1c2ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zvec-tool 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 2mo 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 · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

zvec-tool is a CLI for semantic search over a project knowledge base. It vectorizes documents (regulations, process docs, notes) into a local vector DB so that LLM assistants can retrieve relevant context by meaning, not by keywords.

What gets indexed

You must tell zvec which directory to index — there is no hardcoded default. Pass the path to the index command, or set ZVEC_INDEX_ROOT:

node zvec-tool/zvec.mjs index ./docs
node zvec-tool/zvec.mjs index --root ./docs
# or: ZVEC_INDEX_ROOT=./docs node zvec-tool/zvec.mjs index

By default only *.md files are indexed (ZVEC_EXTENSIONS). Source code, configs (package.json, tsconfig.json, …) are not indexed unless you add their extensions. To search source code or configs, do not use zvec — run a normal grep instead.

How to search

From the project root (the parent of zvec-tool/):

node zvec-tool/zvec.mjs search "<query in RU or EN>" --top 8

Each result contains: the file path, a score (cosine similarity), and a 220-char preview. Scores > 0.7 are strong. Results are sorted by descending score.

Workflow

For questions about business processes, regulations, or project documentation, start with zvec search.
Treat a match as useful only if it directly relates to the query; if hits are only tangential, treat the result as insufficient and refine the query.
If zvec errors or returns 0 results, say so explicitly, then do a focused grep over the relevant directories.
For source code, symbol names, and configs, use grep directly — zvec only indexes the configured document folder.
If both zvec and grep find nothing, tell the user explicitly and ask for clarification (file, symbol, module).

CLI commands

Command	Purpose
`node zvec-tool/zvec.mjs index <path>`	Build / rebuild the index of the given directory (staging → atomic promote)
`node zvec-tool/zvec.mjs search "<q>" [--top N] [--json]`	Semantic search (default `--top 8`)
`node zvec-tool/zvec.mjs status`	Index status (`docCount`, active version)
`node zvec-tool/zvec.mjs doctor`	Diagnostics (probes DB, shows lock holder)
`node zvec-tool/zvec.mjs versions`	List DB versions
`node zvec-tool/zvec.mjs rollback <ver-id>`	Roll back the active version
`node zvec-tool/zvec.mjs backups` / `backup`	List / create a backup

Read the full file on GitHub · 94 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.

2mo ago First seen · 94 lines · 1,439 tokens per session scan A 0c7826a1c2ac

Subscribe to this mod's changes

zvec-tool AGENTS.md is an instructions file published in the GitHub repository alexqem/zvec-tool (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,439 tokens to every session, about $0.0058 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 2026-08-31.

Data and AI RAG and vectors Research

zvec-tool AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
zvec-tool AGENTS.mdalexqem/zvec-tool	Instructions file	2	3mo ago	MIT	A	1,439	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

zvec-tool: Instructions file for Codex