Agent skill

Architecture

by adamthewilliam in adamthewilliam/grepika

This skill should be used when the user asks to "map the architecture", "show module dependencies", "analyze coupling", "dependency graph", "how are modules connected", "module boundaries", or…

MITAuto-check passedDevelopment

Install Architecture

skills CLI
$ npx skills add adamthewilliam/grepika --skill architecture -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install adamthewilliam/grepika architecture --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/adamthewilliam/grepika.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/grepika/skills/architecture .claude/skills/architecture && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
architecture
GitHub stars
138
Token cost
~1.1k tokens
SKILL.md length
307 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

This skill should be used when the user asks to "map the architecture", "show module dependencies", "analyze coupling", "dependency graph", "how are modules connected", "module boundaries", or…

  • Works in 5 steps: Map module boundaries → Trace inter-module dependencies → Identify coupling hotspots → …
  • Asks to map the architecture
  • SKILL.md covers Input, Pre-check, Architecture Analysis Workflow and Output Format, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Architecture is an agent skill from adamthewilliam/grepika. This skill should be used when the user asks to "map the architecture", "show module dependencies", "analyze coupling", "dependency graph", "how are modules connected", "module boundaries", or mentions keywords related to architectural analysis and dependency mapping.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires grepika MCP server.

It sits in Development. It works with Model Context Protocol. The licence is MIT.

When your agent uses it

  • Asks to map the architecture
  • Show module dependencies
  • Analyze coupling
  • Dependency graph

Example prompts

  • “map the architecture”
  • “show module dependencies”
  • “analyze coupling”
  • “/architecture”

Requirements

  • Compatibility (from SKILL.md): Requires grepika MCP server.
  • Pre-approved tools (allowed-tools): mcp__grepika__search, mcp__grepika__refs, mcp__grepika__outline, mcp__grepika__toc, mcp__grepika__get, mcp__grepika__graph, mcp__grepika__structural_search, mcp__grepika__add_workspace

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Map module boundaries
  2. Trace inter-module dependencies
  3. Identify coupling hotspots
  4. Trace data flow
  5. Assess module cohesion

What it can do on your machine

Read from SKILL.md and the folder at commit f035a18. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • mcp__grepika__search
    • mcp__grepika__refs
    • mcp__grepika__outline
    • mcp__grepika__toc
    • mcp__grepika__get
    • mcp__grepika__graph
    • mcp__grepika__structural_search
    • mcp__grepika__add_workspace

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires grepika MCP server.

    From compatibility in the SKILL.md frontmatter.

Context cost

Architecture loads about 1.1k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 307 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from adamthewilliam/grepika at commit f035a18, republished under its MIT licence (© adamthewilliam). 307 words, ~1,056 tokens.

Download SKILL.mdSave it as .claude/skills/architecture/SKILL.md (or your agent's skills folder).
name
architecture
description
This skill should be used when the user asks to "map the architecture", "show module dependencies", "analyze coupling", "dependency graph", "how are modules connected", "module boundaries", or mentions keywords related to architectural analysis and dependency mapping.
allowed-tools
mcp__grepika__search, mcp__grepika__refs, mcp__grepika__outline, mcp__grepika__toc, mcp__grepika__get, mcp__grepika__graph, mcp__grepika__structural_search, mcp__grepika__add_workspace
compatibility
Requires grepika MCP server.
version
1.0.0
disable-model-invocation
true
context
fork
agent
Explore
model
haiku

Architecture Mapping Skill

You are an architecture analyst. Map module boundaries, trace dependencies, and identify coupling patterns across the codebase.

Input

Focus area: $ARGUMENTS

If no area specified, analyze the entire codebase architecture. If an area is specified (e.g., "api layer", "data pipeline", "auth module"), focus the analysis on that subsystem.

Pre-check

If any tool returns "No active workspace", call mcp__grepika__add_workspace with the project root first, then retry the tool.

Architecture Analysis Workflow

  1. Map module boundaries

    • Use mcp__grepika__toc to identify top-level directories and their structure
    • Use mcp__grepika__outline on key files in each directory to understand exports
    • Identify logical modules (e.g., controllers, services, repositories, types)
  2. Trace inter-module dependencies

    • For each module's key exports, use mcp__grepika__refs to find where they're consumed
    • Group the ref_type: "import" results by source module to build the dependency graph
    • Note which modules import from which other modules
    • Use mcp__grepika__graph for indexed imports, dependents, callers, and callees when the index is available
  3. Identify coupling hotspots

    • Find files/symbols with the highest cross-module reference counts
    • Use mcp__grepika__search with mode: "fts" to find shared abstractions
    • Flag tightly coupled modules (bidirectional dependencies)
  4. Trace data flow

    • Use mcp__grepika__refs on key types/interfaces to see how data moves through layers
    • Use mcp__grepika__outline to identify transformation functions
    • Map the path from entry point to storage/output
  5. Assess module cohesion

    • Use mcp__grepika__outline to check if modules have focused responsibilities
    • Flag modules that export unrelated functionality

Output Format

## Architecture Analysis: [focus area or "Full Codebase"]

### Module Map

| Module | Location | Responsibility | Key Exports |
|--------|----------|----------------|-------------|
| [name] | [path/] | [what it does] | [main exports] |

### Dependency Graph

[module-a] ──imports──> [module-b] [module-a] ──imports──> [module-c] [module-b] ──imports──> [module-d] [module-c] ──imports──> [module-d] (shared dependency)


### Coupling Analysis

| Module Pair | Direction | Shared Symbols | Risk |
|-------------|-----------|----------------|------|
| [a] <-> [b] | bidirectional | [count] | high |
| [a] -> [c] | one-way | [count] | low |

### Data Flow

[Entry Point] → [Module A: validate] → [Module B: transform] → [Module C: persist] Types: RequestDTO → DomainModel → Entity


### Hotspots

- **Most imported**: [symbol] — referenced by [N] modules
- **Most complex**: [file] — [N] exports, [M] dependencies
- **Bidirectional coupling**: [module-a] <-> [module-b]

### Architectural Observations

- **Layering**: [describe if layers are clean or leaky]
- **Shared state**: [any global state or singletons]
- **Boundaries**: [where module boundaries are clear vs blurred]

### Recommendations

- [actionable suggestions for improving architecture]

Tips

  • Focus on module-to-module relationships, not individual function calls
  • Bidirectional dependencies between modules are a strong coupling signal
  • Modules with many inbound refs are stability risks — changes ripple widely
  • Look for "god modules" that everything depends on
  • Consider test modules separately from production modules

© adamthewilliam, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/grepika/skills/architecture of adamthewilliam/grepika.

Open the folder on GitHubat commit f035a18

Compare with similar skills

Architecture next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Architecture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Architecture this skilladamthewilliam/grepika138—~1.1kAutomated safety check: PassMIT
Debugging Executionsn8n-io/n8n207k—~2.6kAutomated safety check: PassCustom licence
ast-grep Structural Searchcode-yeongyu/oh-my-openagent70k—~3.3kAutomated safety check: PassMIT
Analyze Logsactivepieces/activepieces25k1 repos~1.6kAutomated safety check: PassMIT
ReleasePrefectHQ/fastmcp28k—~2.9kAutomated safety check: PassApache-2.0
Claude Code Skillcodeaashu/claude-code3.4k1 repos~2.7kAutomated safety check: PassProprietary

Similar skills

  • Official

    Debug failed or wrong-output workflow executions using executions tools.

    207k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • ast-grep Structural Search

    code-yeongyu/oh-my-openagent

    Searches and rewrites code by syntax-tree shape across 25 languages with ast-grep, for codemods, structural queries and YAML lint rules, using a Python wrapper script.

    70k GitHub stars~3.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Analyze Logs

    activepieces/activepieces

    Analyze application logs from the .evlog/logs/ directory. An agent skill from activepieces/activepieces.

    25k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Release

    PrefectHQ/fastmcp

    Cut a FastMCP release end to end. An agent skill from PrefectHQ/fastmcp.

    28k GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Claude Code Skill

    codeaashu/claude-code

    Development conventions and architecture guide for the Claude Code CLI repository.

    3.4k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed
  • Run Nx generators with prioritization for workspace-plugin generators.

    29k GitHub starsUsed in 2 repos~592 tokens
    DevelopmentAuto-check: notes

More from adamthewilliam/grepika

All 9 skills in this repo
  • Impact

    adamthewilliam/grepika

    This skill should be used when the user asks to "analyze impact of changes", "check blast radius", "what would break if I change this", "refactoring safety analysis", or mentions keywords related to…

    138 GitHub stars~794 tokensUpdated 1 mo ago
    Auto-check passed
  • Index Status

    adamthewilliam/grepika

    This skill should be used when the user asks to "check index status", "is the index healthy", "index diagnostics", "search index health", or mentions keywords related to verifying grepika search…

    138 GitHub stars~696 tokensUpdated 1 mo ago
    Auto-check passed
  • Investigate

    adamthewilliam/grepika

    This skill should be used when the user asks to "investigate a bug", "trace an error", "debug this issue", "find where this error comes from", or mentions keywords related to error tracing and bug…

    138 GitHub stars~762 tokensUpdated 1 mo ago
    Auto-check passed
  • Learn Codebase

    adamthewilliam/grepika

    This skill should be used when the user asks to "learn this codebase", "give me a codebase overview", "onboard me to this project", "explain the architecture", or mentions keywords related to…

    138 GitHub stars~922 tokensUpdated 1 mo ago
    Auto-check passed
  • Apply Pattern

    adamthewilliam/grepika

    This skill should be used when the user asks to "apply a pattern", "use a blueprint", "implement [pattern] from [source]", "what blueprints do I have", "list patterns", "adapt this pattern", or…

    138 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check: notes
  • Diff Files

    adamthewilliam/grepika

    This skill should be used when the user asks to "compare files", "diff these files", "what changed between", "show differences between", "compare versions", or mentions keywords related to file…

    138 GitHub stars~819 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Architecture

What does Architecture do?

This skill should be used when the user asks to "map the architecture", "show module dependencies", "analyze coupling", "dependency graph", "how are modules connected", "module boundaries", or…. Architecture is an agent skill from adamthewilliam/grepika. This skill should be used when the user asks to "map the architecture", "show module dependencies", "analyze coupling", "dependency graph", "how are modules connected", "module boundaries", or mentions keywords related to architectural analysis and dependency mapping.

When should I use Architecture?

Architecture fits situations like: asks to map the architecture; show module dependencies; analyze coupling; dependency graph.

How do I install Architecture in Claude Code?

Run `npx skills add adamthewilliam/grepika --skill architecture -a claude-code`. Or copy the skill folder (plugins/grepika/skills/architecture in adamthewilliam/grepika) into .claude/skills/architecture in your project. Claude Code loads it when a task matches its description.

How do I install Architecture in Codex?

Run `npx skills add adamthewilliam/grepika --skill architecture -a codex`. Or copy the skill folder (plugins/grepika/skills/architecture in adamthewilliam/grepika) into .agents/skills/architecture in your project. Codex loads it when a task matches its description.

Can I use Architecture in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add adamthewilliam/grepika --skill architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architecture, .gemini/skills/architecture, .github/skills/architecture and .opencode/skills/architecture in your project.

What does Architecture need to run?

SKILL.md names no scripts, command-line tools or credentials: Architecture is instructions for the agent only. Its frontmatter pre-approves these tools: mcp__grepika__search, mcp__grepika__refs, mcp__grepika__outline, mcp__grepika__toc, mcp__grepika__get, mcp__grepika__graph, mcp__grepika__structural_search, mcp__grepika__add_workspace. Compatibility (from SKILL.md): Requires grepika MCP server..

Does Architecture access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Architecture safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Architecture use?

Architecture is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Architecture use?

About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Architecture?

Skills that share tags, products or a category with Architecture: Debugging Executions (n8n-io/n8n, 207k stars), ast-grep Structural Search (code-yeongyu/oh-my-openagent, 70k stars), Analyze Logs (activepieces/activepieces, 25k stars) and Release (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architecture?

adamthewilliam (a GitHub user) maintains it in adamthewilliam/grepika, which has 138 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on August 12, 2026.

Source: adamthewilliam/grepika on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.