add-feature

A command for adding a feature to Code-Index-MCP, a code-indexing project, while following its plugin-based structure.

In plain words
What is it for?
It helps add language plugins, core features, utilities, integration plans, and related test and agent-guidance files.
Why use it?
It turns a feature request into planned architecture, implementation files, dependencies, and tests that match the project's conventions.

Command for Claude Code

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 commands/consiliency/code-index-mcp/add-feature
Clone the repo
git clone --depth 1 https://github.com/Consiliency/Code-Index-MCP

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,928 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.01928
Opus 5 $0.00000 $0.00964
Sonnet 5 $0.00000 $0.00386
Haiku 4.5 $0.00000 $0.00193

Measured 2d ago against content hash b0fd87c75af3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-feature 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.

.claude/commands/add-feature.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

add-feature

Add a new feature to Code-Index-MCP following the plugin-based architecture.

Feature: $ARGUMENTS[0] (Type: $ARGUMENTS[1])

1. Planning Phase

  • Define feature scope and requirements
  • Determine if it's a new plugin, core feature, or utility
  • Identify dependencies (Tree-sitter grammars, external libraries)
  • Plan integration with existing components

2. Architecture Design

For New Language Plugin:
mcp_server/
├── plugins/
│   └── $ARGUMENTS[0]_plugin/
│       ├── __init__.py
│       ├── plugin.py           # Implements IPlugin interface
│       ├── AGENTS.md          # AI agent configuration
│       └── CLAUDE.md          # Points to AGENTS.md for instructions
For Core Feature:
mcp_server/
├── $ARGUMENTS[0].py           # Core implementation
├── utils/
│   └── $ARGUMENTS[0]_helper.py # Supporting utilities
└── tests/
    └── test_$ARGUMENTS[0].py  # Unit tests

3. Plugin Implementation Template

# mcp_server/plugins/$ARGUMENTS[0]_plugin/plugin.py
from pathlib import Path
from typing import Iterable

from ...plugin_base import (
    IPlugin, IndexShard, SymbolDef, 
    Reference, SearchResult, SearchOpts
)
from ...utils.treesitter_wrapper import TreeSitterWrapper

class Plugin(IPlugin):
    lang = "$ARGUMENTS[0]"
    
    def __init__(self) -> None:
        self._ts = TreeSitterWrapper()
        # Initialize language-specific components
    
    def supports(self, path: str | Path) -> bool:
        """Check if file extension matches plugin."""
        return Path(path).suffix in {".ext", ".extension"}
    
    def indexFile(self, path: str | Path, content: str) -> IndexShard:
        """Parse and index file content."""
        # Implementation using tree-sitter
        pass
    
    def getDefinition(self, symbol: str) -> SymbolDef | None:
        """Find symbol definition."""
        pass
    
    def findReferences(self, symbol: str) -> Iterable[Reference]:
        """Find all references to symbol."""
        pass
    
    def search(self, query: str, opts: SearchOpts | None = None) -> Iterable[SearchResult]:
        """Search for code patterns."""
        pass

Read the full file on GitHub · 270 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 · 270 lines · 0 tokens per session scan A b0fd87c75af3

Subscribe to this mod's changes

add-feature is a command published in the GitHub repository Consiliency/Code-Index-MCP (57 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,928 tokens. 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 2026-08-30.