Skip to content
Agentmart
Submit a tool

deepsearch

Exhaustive multi-strategy codebase search using grep, ripgrep, find, and AST-aware tracing to locate implementations, references, dependencies, and usage…

Skill by MeroZemory

IndexedMIT★ 28
Write a review

Chalk Labs

Need help deploying deepsearch?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/merozemory-deepsearch

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Exhaustive multi-strategy codebase search using grep, ripgrep, find, and AST-aware tracing to locate implementations, references, dependencies, and usage patterns for a given symbol, pattern, or concept. Use when you need to find every occurrence of a function, type, config key, or concept across a project — especially when simple text search misses indirect references, re-exports, or dynamic usage.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/deepsearch

What's inside

Skill name
deepsearch
Description
Exhaustive multi-strategy codebase search using grep, ripgrep, find, and AST-aware tracing to locate implementations, references, dependencies, and usage patterns for a given symbol, pattern, or concept. Use when you need to find every occurrence of a function, type, config key, or concept across a project — especially when simple text search misses indirect references, re-exports, or dynamic usage.
License
MIT
Instructions
143 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Deep Search

## Objective

Perform an exhaustive, multi-pass search of the codebase for the specified query, pattern, or concept. Go beyond naive text matching by combining literal search, regex patterns, structural analysis, and dependency tracing to produce a complete map of where and how the target appears.

## Phase 1 — Literal and Regex Search

Start broad. Run parallel searches to catch exact matches, variations, and related terms.

### Exact identifier search

```bash
# Case-sensitive exact match across the project (ripgrep)
rg --word-regexp 'FunctionName' --type-add 'src:*.{ts,tsx,js,jsx,py,go,rs,java}' -t src -n

# If ripgrep is unavailable, fall back to grep
grep -rn --include='*.ts' --include='*.tsx' 'FunctionName' src/
```

### Case-insensitive and partial matches

```bash
# Catch naming-convention variants (camelCase, snake_case, SCREAMING_CASE)
rg -in 'function.name|function_name|FUNCTION_NAME' --glob '!node_modules' --glob '!dist'
```

### Regex pattern search

```bash
# Find all call sites, including method calls and chained usage
rg 'functionName\s*\(' -n --glob '*.{ts,tsx,js,jsx}'

# Find type annotations, generic usage, and interface references
rg ':\s*FunctionName[<\s,\)]' -n --glob '*.{ts,tsx}'

# Find decorators or annotations referencing the target
rg '@FunctionName|@.*FunctionName' -n
```

### File and path search

```bash
# Find files whose name matches the concept
find . -type f \( -name '*function-name*' -o -name '*FunctionName*' \) -not -path '*/node_modules/*'

# Find config or manifest entries
rg 'function.name|functionName' -g '*.{json,yaml,yml,toml,ini,env}'
```

## Phase 2 — Structural and Dependency Tracing

Move beyond text matching to understand the dependency graph around the target.

### Import/export tracing

```bash
# Who imports this symbol?
rg "import.*FunctionName.*from" -n --glob '*.{ts,tsx,js,jsx}'
rg "from\s+['\"].*function-name['\"]" -n --glob '*.{ts,tsx,js,jsx}'

# Who re-exports it? (barrel files, index files)
rg "export.*FunctionName|export \* from.*function-name" -n --glob '*.{ts,tsx,js,jsx}'

# For Python
rg "from\s+\S+\s+import\s+.*FunctionName" -n --glob '*.py'
```

### Reverse dependency walk

For each file that contains the target, ask: "What imports this file?"

```bash
# Extract the module path from the file, then search for imports of that path
rg "from ['\"].*modules/target-module['\"]" -n --glob '*.{ts,tsx,js,jsx}'
```

### Dynamic and indirect references

```bash
# String-based lookups (config keys, event names, route paths)
rg "'function.name'|\"function.name\"|`function.name`" -n

# Object bracket access
rg "\[.*['\"]functionName['\"].*\]" -n

# Reflection, decorators, or registry patterns
rg "register\(.*functionName|resolve\(.*functionName" -n
```

## Phase 3 — Contextual Deep Dive

Read the files identified in Phases 1 and 2 to understand context.

### For each match cluster

1. **Read the surrounding code** (20-30 lines of context) to understand the role of the target at that location.
2. **Check function signatures and type definitions** to understand the contract.
3. **Trace data flow**: Where does the input come from? Where does the output go?
4. **Identify test files**: Search for test files covering the target.

```bash
# Find related test files
find . -type f \( -name '*FunctionName*test*' -o -name '*FunctionName*spec*' -o -name '*test*FunctionName*' \) -not -path '*/node_modules/*'

# Search test content for usage
rg 'FunctionName' --glob '*{test,spec}*.{ts,tsx,js,jsx,py}'
```

### Framework-specific locations to check

- **React/Next.js**: `components/`, `hooks/`, `pages/`, `app/`, `lib/`, `utils/`, `services/`, `store/`, `context/`
- **Express/Fastify**: `routes/`, `middleware/`, `controllers/`, `handlers/`
- **Python/Django**: `views/`, `models/`, `serializers/`, `urls.py`, `tasks/`
- **Go**: Check `cmd/`, `internal/`, `pkg/`, plus any `*_test.go` files
- **Config/infra**: `.env*`, `docker-compose*`, `Dockerfile`, `*.yaml`, `*.toml`, CI workflow files

## Phase 4 — Synthesize and Report

From MeroZemory/oh-my-droid, MIT.

More from MeroZemory/oh-my-droid

Signals

Stars
28
Forks
7
Open issues
1
Last commit (this folder)
Apr 17, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from MeroZemory

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get deepsearch running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying deepsearch?

CallGet help
Cite this page

deepsearch skill. Agent Mart. https://agentmart.dev/skills/merozemory-deepsearch (last updated 2026-10-24)