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.
npx agentmods add instructions/abivan-tech/zvec-mcp/agents-mdgit clone --depth 1 https://github.com/ABIvan-Tech/zvec-mcpWhat 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 | $0.01264 | $0.01264 |
| Opus 5 | $0.00632 | $0.00632 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
zvec-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
For repository and implementation questions, first consult the local project knowledge base through the MCP tool search_project_knowledge before doing any broad repository search. If search_project_knowledge returns a tool error or is unavailable, do not silently continue as if the knowledge base had been checked successfully; explicitly mention that the MCP knowledge base was unavailable and then fall back to a targeted grep search. If search_project_knowledge returns no useful results, explain that the knowledge base did not provide a useful hit and then proceed to a focused grep search.
[!NOTE] The database indexes source files only. Files with extensions like
.md(documentation), configuration files (package.json,tsconfig.json,vite.config.ts,eslint.config.js), and declaration files (.d.ts) are ignored by design. For these files or queries about general architecture/configs, skip vector search and usegrep_searchorview_filedirectly. If the MCP tool throws locking/concurrency errors (e.g.Can't lock collection), it may mean there are stale bridge processes holding the file lock. Proactively list and terminate any stalenode zvec-mcp-bridge.jsprocesses. If the index seems outdated or returns zero results on valid codebase queries, callinitialize_project_knowledgewithforce_rebuild: trueto regenerate the database.Architecture: The bridge runs in one of three modes:
--daemon --port N— persistent HTTP/SSE daemon (shared by multiple clients)- Default (auto) — auto-starts a daemon if none running, otherwise proxies to existing one
- Legacy stdio — runs standalone (fallback if daemon can't start)
Available MCP Tools
| Tool | Description |
|---|---|
search_project_knowledge |
Semantic search through the indexed project codebase. Use as first step before broad repository search. |
initialize_project_knowledge |
Create or rebuild the knowledge base index. Call when index is missing, stale, or corrupted. |
index_file |
Force indexing of a specific file immediately. Useful for newly created or modified files. |
get_knowledge_status |
Get health, statistics, and configuration (document count, init state, detected extensions, project type). |
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 First seen · 71 lines · 1,264 tokens per session scan A 07d4df5843d0
zvec-mcp AGENTS.md is an instructions file published in the GitHub repository ABIvan-Tech/zvec-mcp (9 stars, last pushed 2mo ago), licensed MIT. It adds 1,264 tokens to every session, about $0.0063 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.
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.
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).
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.
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.
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).
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.