Necmttn

Context-gathering setup for Claude Code

A small bundle that makes Claude Code's review/debug/build workflows sharper without burning tokens on blind file reads.

What's in here

File	Type	Where it goes
SKILL-composto.md	Skill	~/.claude/skills/composto/SKILL.md
agent-codebase-locator.md	Agent	~/.claude/agents/codebase-locator.md

Necmttn

name	codebase-analyzer
description	Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :)
tools	Read, Grep, Glob, LS

You are a specialist at understanding HOW code works. Your job is to analyze implementation details, trace data flow, and explain technical workings with precise file:line references.

Core Responsibilities

Necmttn

/review-all - Phase 1: Context Gathering

Before running reviewers on a diff, gather context the diff alone can't show. Run these three subagents in parallel:

Parallel context subagents

• codebase-locator - find callers/consumers of changed symbols (integration surface not in the diff). Catches "this edit breaks a caller nobody looked at."

• codebase-pattern-finder - find existing patterns for what the diff introduces. Catches "Claude reinvented a helper that already exists."

Necmttn

# Copy your Osome cookies here
# Get from: DevTools → Network → any request to my.osome.com → Headers → Cookie
OSOME_COOKIES="your_cookie_string_here"

Necmttn

import * as z from "zod";
/**
 * This function converts a JSON schema into a Zod schema.
 * 
 * @param schema The JSON schema to be converted. The schema should follow the JSON Schema Draft 7 specification.
 * 
 * Example:
 *            schema: {
 *              $schema: "http://json-schema.org/draft-07/schema#",
 *              title: "Complex Example",

Necmttn

import {
  createParser,
  ParsedEvent,
  ReconnectInterval,
} from "eventsource-parser";
import { Procedure } from "./procedure";
import openai, { ChatCompletionRequestMessage } from "@acme/openai";
import _ from "lodash";

export type Message = Omit<ChatCompletionRequestMessage, "role"> & {

Necmttn

export const generateFilter = (filterParams) => {
  const IDL_DEFINATION = {
    name: "vote",
    type: {
      kind: "struct",
      fields: [
        {
          name: "proposalId",
          type: "u64",
        },

Necmttn

const createDisctionaryOfColumns = (tableDefination)  => {
    return tableDefination.split(',').reduce((prev,column) => {
        const part = column.trim().split(/\s+/);
        console.log(part)
        const cName = part[0];
        const type = part[1];
        prev[cName]= type;
        return prev;
    }, {})
}

Necmttn

const REQUEST = 'REQUEST'
const SUCCESS = 'SUCCESS'
const FAILURE = 'FAILURE'

function action(type, payload = {}) {
  return {type, ...payload}
}

const listJDs = {
  request: () => action(ActionTypes.LIST_JDS[REQUEST]),

Necmttn

const winston = require('winston');

const logger = winston.createLogger({
  level: 'debug',
//  (typeof(process.env.NODE_ENV) === 'string' && process.env.NODE_ENV.startsWith('prod'))
//    ? 'info'
//    : 'debug',
  format: winston.format.combine(
    winston.format.timestamp(),
    winston.format.splat(),