map-codebase

Name: map-codebase
Author: tobihagemann

3installs29forks

How to install map-codebase?

tobihagemann/turbo/map-codebase

$npx -y skills add tobihagemann/turbo --skill map-codebase

Installs into the current project.

Summary

Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.

Files · 1

View on GitHub

SKILL.md

1	# Map Codebase
2
3	Deep architecture report. Fans out parallel inspections across different aspects of the codebase, synthesizes their findings, and writes `.turbo/codebase-map.md` and `.turbo/codebase-map.html`. Analysis-only.
4
5	## Task Tracking
6
7	At the start, use `TaskCreate` to create a task for each phase:
8
9	1. Scope
10	2. Launch inspection agents
11	3. Synthesize and generate markdown report
12	4. Generate HTML report
13
14	## Step 1: Scope
15
16	If `$ARGUMENTS` specifies paths, use those directly (skip the question).
17
18	Otherwise, use `AskUserQuestion` to confirm scope:
19
20	- Entire codebase — inspect everything
21	- Specific paths — user provides directories or file patterns
22
23	Once scope is determined, glob for source files in the selected scope. Exclude generated and vendored directories (`node_modules/`, `dist/`, `build/`, `vendor/`, `__pycache__/`, `.build/`, `DerivedData/`, `target/`, `.tox/`, and others appropriate to the project).
24
25	Build a file manifest grouped by top-level source directory. This manifest is shared with all agents as a starting point. Agents may explore beyond it based on what they discover.
26
27	## Step 2: Launch Inspection Agents
28
29	Use the Agent tool to launch all 7 agents below in a single assistant message so they run concurrently. Run them in the foreground so all their results return in this turn. Each Agent call uses `model: "opus"`. Each agent receives the scoped file manifest and its exploration brief, and its prompt directs it to treat the shared working tree and its git index as read-only — any empirical check runs in an isolated `git worktree` the agent discards afterward.
30
31	### Dimensions
32
33	Launch one agent per dimension. Each agent's prompt provides the file manifest and the exploration brief below. Agents explore adaptively: go deeper where complexity warrants it, stay high-level where things are straightforward. Findings should be concrete (reference specific files and directories) rather than generic.
34
35	\| # \| Dimension \| Exploration Brief \|
36	\|---\|---\|---\|
37	\| 1 \| Project Structure \| Map directory layout, module organization, naming conventions, and file roles. Identify the organizing principle (feature-based, layer-based, hybrid). Note generated or build output directories. \|
38	\| 2 \| Tech Stack and Build System \| Identify languages, frameworks, package managers, build tools, and runtime requirements. Note version constraints and compatibility targets. \|
39	\| 3 \| Entry Points and Public API \| Find how the system is invoked: CLI commands, HTTP endpoints, event handlers, exported modules, main functions. Map the public surface area. \|
40	\| 4 \| Core Abstractions and Patterns \| Identify key types, classes, interfaces, and design patterns. Note architectural patterns (MVC, plugin system, pipeline, etc.) and how they shape the code. \|
41	\| 5 \| Data Flow and State \| Trace how data enters, transforms, persists, and exits the system. Identify state management approaches, storage layers, and data boundaries. \|
42	\| 6 \| External Dependencies and Integrations \| Map third-party services, APIs, databases, and system boundaries. Note how external dependencies are abstracted or coupled. \|
43	\| 7 \| Testing and Quality Infrastructure \| Describe the test strategy: frameworks, coverage approach, test organization, CI/CD pipeline. Note gaps or unusual patterns. \|
44
45	Each agent writes its findings as structured markdown with sections and subsections.
46
47	## Step 3: Synthesize and Generate Markdown Report
48
49	After all agents complete:
50
51	1. Read all agent reports.
52	2. Identify cross-cutting themes, connections between dimensions, and architectural trade-offs.
53	3. Write a brief executive summary (3-5 sentences) capturing the system's essential character.
54	4. Resolve contradictions or overlaps between dimension reports.
55	5. Write `.turbo/codebase-map.md` using the report template. Output the executive summary as text before writing the file.
56
57	### Report Template
58
59	```markdown
60	# Codebase Map
61
62	Date: <date>
63	Scope: <what was inspected>
64
65	## Executive Summary
66
67	<3-5 sentences: what the system is, how it's organized, what architectural choices define it>
68
69	## Project Structure
70
71	<from dimension 1>
72
73	## Tech Stack
74
75	<from dimension 2>
76
77	## Entry Points and API
78
79	<from dimension 3>
80
81	## Core Abstractions
82
83	<from dimension 4>
84
85	## Data Flow
86
87	<from dimension 5>
88
89	## External Dependencies
90
91	<from dimension 6>
92
93	## Testing and Quality
94
95	<from dimension 7>
96
97	## Cross-Cutting Observations
98
99	<themes, trade-offs, and connections identified during synthesis>
100	```

People who liked this also viewed

6 picks

Type

map-codebase

3installs29forks

View on GitHub

How to install map-codebase?

tobihagemann/turbo/map-codebase

$npx -y skills add tobihagemann/turbo --skill map-codebase

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Map Codebase
2
3	Deep architecture report. Fans out parallel inspections across different aspects of the codebase, synthesizes their findings, and writes `.turbo/codebase-map.md` and `.turbo/codebase-map.html`. Analysis-only.
4
5	## Task Tracking
6
7	At the start, use `TaskCreate` to create a task for each phase:
8
9	1. Scope
10	2. Launch inspection agents
11	3. Synthesize and generate markdown report
12	4. Generate HTML report
13
14	## Step 1: Scope
15
16	If `$ARGUMENTS` specifies paths, use those directly (skip the question).
17
18	Otherwise, use `AskUserQuestion` to confirm scope:
19
20	- Entire codebase — inspect everything
21	- Specific paths — user provides directories or file patterns
22
23	Once scope is determined, glob for source files in the selected scope. Exclude generated and vendored directories (`node_modules/`, `dist/`, `build/`, `vendor/`, `__pycache__/`, `.build/`, `DerivedData/`, `target/`, `.tox/`, and others appropriate to the project).
24
25	Build a file manifest grouped by top-level source directory. This manifest is shared with all agents as a starting point. Agents may explore beyond it based on what they discover.
26
27	## Step 2: Launch Inspection Agents
28
29	Use the Agent tool to launch all 7 agents below in a single assistant message so they run concurrently. Run them in the foreground so all their results return in this turn. Each Agent call uses `model: "opus"`. Each agent receives the scoped file manifest and its exploration brief, and its prompt directs it to treat the shared working tree and its git index as read-only — any empirical check runs in an isolated `git worktree` the agent discards afterward.
30
31	### Dimensions
32
33	Launch one agent per dimension. Each agent's prompt provides the file manifest and the exploration brief below. Agents explore adaptively: go deeper where complexity warrants it, stay high-level where things are straightforward. Findings should be concrete (reference specific files and directories) rather than generic.
34
35	\| # \| Dimension \| Exploration Brief \|
36	\|---\|---\|---\|
37	\| 1 \| Project Structure \| Map directory layout, module organization, naming conventions, and file roles. Identify the organizing principle (feature-based, layer-based, hybrid). Note generated or build output directories. \|
38	\| 2 \| Tech Stack and Build System \| Identify languages, frameworks, package managers, build tools, and runtime requirements. Note version constraints and compatibility targets. \|
39	\| 3 \| Entry Points and Public API \| Find how the system is invoked: CLI commands, HTTP endpoints, event handlers, exported modules, main functions. Map the public surface area. \|
40	\| 4 \| Core Abstractions and Patterns \| Identify key types, classes, interfaces, and design patterns. Note architectural patterns (MVC, plugin system, pipeline, etc.) and how they shape the code. \|
41	\| 5 \| Data Flow and State \| Trace how data enters, transforms, persists, and exits the system. Identify state management approaches, storage layers, and data boundaries. \|
42	\| 6 \| External Dependencies and Integrations \| Map third-party services, APIs, databases, and system boundaries. Note how external dependencies are abstracted or coupled. \|
43	\| 7 \| Testing and Quality Infrastructure \| Describe the test strategy: frameworks, coverage approach, test organization, CI/CD pipeline. Note gaps or unusual patterns. \|
44
45	Each agent writes its findings as structured markdown with sections and subsections.
46
47	## Step 3: Synthesize and Generate Markdown Report
48
49	After all agents complete:
50
51	1. Read all agent reports.
52	2. Identify cross-cutting themes, connections between dimensions, and architectural trade-offs.
53	3. Write a brief executive summary (3-5 sentences) capturing the system's essential character.
54	4. Resolve contradictions or overlaps between dimension reports.
55	5. Write `.turbo/codebase-map.md` using the report template. Output the executive summary as text before writing the file.
56
57	### Report Template
58
59	```markdown
60	# Codebase Map
61
62	Date: <date>
63	Scope: <what was inspected>
64
65	## Executive Summary
66
67	<3-5 sentences: what the system is, how it's organized, what architectural choices define it>
68
69	## Project Structure
70
71	<from dimension 1>
72
73	## Tech Stack
74
75	<from dimension 2>
76
77	## Entry Points and API
78
79	<from dimension 3>
80
81	## Core Abstractions
82
83	<from dimension 4>
84
85	## Data Flow
86
87	<from dimension 5>
88
89	## External Dependencies
90
91	<from dimension 6>
92
93	## Testing and Quality
94
95	<from dimension 7>
96
97	## Cross-Cutting Observations
98
99	<themes, trade-offs, and connections identified during synthesis>
100	```

People who liked this also viewed

6 picks

Type