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/xsaven/vector-task-mcp/claude-mdgit clone --depth 1 https://github.com/Xsaven/vector-task-mcpWrote 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.
[](https://agentmods.dev/instructions/xsaven/vector-task-mcp/claude-md)<a href="https://agentmods.dev/instructions/xsaven/vector-task-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/xsaven/vector-task-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01948 | $0.01948 |
| Opus 5 | $0.00974 | $0.00974 |
| Sonnet 5 | $0.00390 | $0.00390 |
| Haiku 4.5 | $0.00195 | $0.00195 |
Grade A, and why
vector-task-mcp CLAUDE.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 3d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vector Task MCP Server
Project Overview
MCP (Model Context Protocol) Server для управління задачами з використанням sqlite-vec для семантичного пошуку.
Technology Stack
- Python: 3.11.8 (requires >= 3.10)
- Package Manager:
uv(сучасний Python package manager) - Database: SQLite 3.43.2 + sqlite-vec extension
- Embeddings: sentence-transformers/all-MiniLM-L6-v2 (384-dimensional vectors)
- MCP Framework: FastMCP >= 0.3.0
Key Dependencies
mcp>=0.3.0- Model Context Protocol frameworksqlite-vec>=0.1.6- Vector search extension для SQLitesentence-transformers>=2.2.2- Embedding models
Project Structure
main.py- Entry point with uv script configurationrequirements.txt- Python dependencies for pip/venv compatibilitypyproject.toml- Modern Python project configuration.python-version- Python version specification (3.11)claude-desktop-config.example.json- Claude Desktop configuration templatesrc/models.py- Data models and configurationsrc/security.py- Security validation and sanitizationsrc/task_store.py- Vector task storage operationstasks.db- SQLite database for tasks
How to Run
Standalone
# Using uv (requires Python with SQLite extensions support)
uv run main.py --working-dir ./
# Alternative with conda Python (has SQLite extensions support)
~/miniconda3/envs/vector-mcp/bin/python main.py --working-dir ./
Configuration Options
-
--working-dir- Working directory for task database (required, default: current directory)- Specifies the project directory where the
memory/subdirectory will be created - Database will be stored at
{working-dir}/memory/tasks.db - Example:
--working-dir /path/to/project→ database at/path/to/project/memory/tasks.db
- Specifies the project directory where the
-
--task-folder- Optional root directory for per-task folders (feature opt-in)- When set, every ROOT task gets its own folder named by its
code(e.g.{--task-folder}/FEAT-44/) plus a generatedtask.mdtemplate. - Subtasks NEVER receive folders — only root tasks (
parent_id IS NULL). - Status transitions rename/archive the folder automatically:
completed → -on-review,done → Archive/{code}(top-level Archive),completed → in_progressreverts the rename. - Filesystem failures NEVER block DB operations — the manager logs warnings and returns silently. DB state is the source of truth.
- Read APIs:
task_getreturnsfolder_path+folder_filesfor root tasks;task_folder_files(task_id|code)returns the same listing on demand. - Example:
--task-folder /path/to/project/tasks→ root taskFEAT-12gets/path/to/project/tasks/FEAT-12/task.md.
- When set, every ROOT task gets its own folder named by its
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.
- 3d ago First seen · 167 lines · 1,948 tokens per session scan A 93a3f5fc0830
vector-task-mcp CLAUDE.md is an instructions file published in the GitHub repository Xsaven/vector-task-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,948 tokens to every session, about $0.0097 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
beads-rs AGENTS.md
Instructions for delightful-ai/beads-rs, covering beads-rs, worldview, architecture, cross-cutting invariants and design references.
kannon CLAUDE.md
Claude Code instructions for kannon-email/kannon, covering database migrations (dbmate), commit messages, agent skills, issue tracker and triage labels.
lms-front AGENTS.md
AGENTS.md instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, development and database (supabase).
lms-front CLAUDE.md
Claude Code instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, architecture and multi-tenancy.
skillsboard AGENTS.md
AGENTS.md instructions for TommyBez/skillsboard, covering agents.md, cursor cloud specific instructions, what this is, running locally and database schema.
skywalking-banyandb CLAUDE.md
Claude Code instructions for apache/skywalking-banyandb, a project described as: An observability database aims to ingest, analyze and store Metrics, Tracing and Logging data.