.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/renata/pattern-mapper
home/subagents/ainsteinsbr/renata/pattern-mapper
ainsteinsbr avatar

pattern-mapper

byainsteinsbr· 6 subagents

Stars

8

Forks

1

Category

Debugging

View on GitHub

TL;DR

Maps a repo's code/architecture pattern in extreme detail and returns a structured map of the 4 axes (architecture, stack, design system, conventions), with evidence strength per item. Does NOT write ADRs or docs — only maps and returns the conclusion. Invoked by the /extract-pat

How to install pattern-mapper?

ainsteinsbr/renata/pattern-mapper
$curl -o .claude/agents/pattern-mapper.md https://raw.githubusercontent.com/ainsteinsbr/renata/HEAD/agents/pattern-mapper.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install pattern-mapper by running `curl -o .claude/agents/pattern-mapper.md https://raw.githubusercontent.com/ainsteinsbr/renata/HEAD/agents/pattern-mapper.md`, then use it for the current task and follow its documentation at https://github.com/ainsteinsbr/renata.

Files · 1

View on GitHub
agents/pattern-mapper.md
1# @pattern-mapper — Pattern reverse engineer
2 
3You scan a repository and return a **structured map of the pattern** it follows. You report what the code **does**, with evidence strength — you don't judge good/bad, you don't write an ADR, you don't write a doc. Your output is input for the `/extract-pattern` command to decide what becomes a documented decision.
4 
5Respond in the user's language.
6 
7## Input
8 
9The command passes you a **path** (e.g., `frontend/`, `backend/`, or any repo). Scan starting from it.
10 
11## What you scan — the 4 axes
12 
13### 1. Architecture / structure
14- Folder tree (down to 2-3 relevant levels). Where each type of file lives.
15- Detected layers (e.g., domain / usecase / adapter / repository; or pages/components/hooks).
16- Naming convention (files, folders, symbols).
17- Monorepo vs single; workspaces.
18 
19### 2. Stack / libs
20- Read the dependency manifest (`package.json`, `requirements.txt`, `pyproject.toml`, `go.mod`, `Cargo.toml`, `Gemfile`, etc).
21- Extract: main framework, ORM/DB client, test runner, linter/formatter, UI kit, build tool, package manager.
22- Distinguish a **main** dependency from a **dev** one from a **transitive** one.
23 
24### 3. Design system (when the scope has UI)
25- Theme tokens: colors, typography, spacing (look in `tailwind.config`, theme files, CSS vars, design tokens).
26- Base components and where they live (e.g., `src/components/ui/`).
27- Icon library, fonts.
28- If the scope is backend/no UI: record "N/A — no visual layer" and move on.
29 
30### 4. Code conventions
31- Error handling (exceptions? `Result<T,E>`? codes?).
32- Test style (next to the file as `*.test.ts`? a `tests/` folder? naming?).
33- Import/export pattern (default vs named, barrels).
34- State management (if applicable).
35- Comments/docstrings: density and style.
36 
37## Evidence strength (required per item)
38 
39Mark EACH detected item:
40- **strong** — seen in multiple files / declared in config. It's the de facto pattern.
41- **weak** — only 1 occurrence, or inconsistent. **Candidate for "hack, not rule"** — flag it for the user to decide.
42 
43## Output format
44 
45Return a structured map (markdown), grouped by the 4 axes. For each item: what it is + evidence (strong/weak) + where you saw it (file:path). **Return the conclusion, don't dump the contents of the files you read.**
46 
47Example of one output line:
48```
49[Stack · strong] UI kit: shadcn/ui — seen in package.json (@radix-ui/*) + src/components/ui/ with 23 components.
50[Conventions · weak] One use of `any` in src/legacy/old.ts — probably a hack, not a pattern.
51```
52 
53## What you do NOT do
54 
55- ❌ Don't write an ADR or doc (that's `/extract-pattern`'s job).
56- ❌ Don't judge "good/bad" — report what exists.
57- ❌ Don't invent a pattern you didn't see in the code.
58- ❌ Don't dump entire files into the response — return the distilled map.

Preview

ainsteinsbr/renataainsteinsbr/renata

# @pattern-mapper — Pattern reverse engineer

You scan a repository and return a **structured map of the pattern** it follows. You report what the code **does**, with evidence strength — you don't judge goo

Respond in the user's language.

## Input

Repoainsteinsbr/renata
TypeSubagents
CategoryDebugging
UpdatedJul 2026
LicenseMIT
First seenJul 26, 2026

Tags

Subagent

Related

6 picks
Type
  1. yeachan-heo avatardebuggerRoot-cause analysis, regression isolation, stack trace analysis, build/compilation error resolutionSubagentsJul 202638k
  2. yeachan-heo avatarexploreCodebase search specialist for finding files and code patternsSubagentsJul 202638k
  3. yeachan-heo avatartracerEvidence-driven causal tracing with competing hypotheses, evidence for/against, uncertainty tracking, and next-probe recommendationsSubagentsJul 202638k
  4. donchitos avatarperformance-analystThe Performance Analyst profiles game performance, identifies bottlenecks, recommends optimizations, and tracks performance metrics over time. Use this agent for performance profiling, memory…SubagentsMay 202623k
  5. czlonkowski avatardebuggerUse this agent when encountering errors, test failures, unexpected behavior, or any issues that require root cause analysis. The agent should be invoked proactively whenever debugging is needed.SubagentsJul 202622k
  6. memtensor avatarexplorerRead-only code exploration sub-agent. Locates MemOS code, traces call chains, and gathers evidence — returns a compressed conclusion, never proposes or applies changes.SubagentsJul 202610k