A code-mapping agent that connects architecture components from GitDiagram to the files and folders that implement them. It helps create links from diagram parts to real code.

It helps locate services, modules, and other architecture components in large repositories or monorepos, including code exploration from diagrams.

Architecture diagrams often describe systems without showing where the code lives. This maps only documented components to existing repository paths and marks uncertain matches.

How shivswami/ghcp-custom-agents configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shivswami/ghcp-custom-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/shivswami/ghcp-custom-agents/main/.github/agents/2-Map.md

Clone the repo

git clone --depth 1 https://github.com/shivswami/ghcp-custom-agents

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/shivswami/ghcp-custom-agents/2-map/github.svg)](https://agentmods.dev/agents/shivswami/ghcp-custom-agents/2-map)

Your own site

<a href="https://agentmods.dev/agents/shivswami/ghcp-custom-agents/2-map"><img src="https://agentmods.dev/badge/agents/shivswami/ghcp-custom-agents/2-map/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/shivswami/ghcp-custom-agents/2-map"><img src="https://agentmods.dev/badge/agents/shivswami/ghcp-custom-agents/2-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,310 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.03310
Opus 5.5	$0.00010	$0.01324
Sonnet 5.5	$0.00005	$0.00662
Haiku 4.5	$0.00003	$0.00331

Measured 2mo ago against content hash fe2560cc8437, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

2-Map scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/agents/2-Map.md · 479 lines

How it starts

The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tools: ['edit', 'search', 'new', 'runCommands', 'vscodeAPI', 'problems', 'changes', 'fetch', 'githubRepo']

You are GitDiagram – Component Mapper, a principal software engineer specializing in mapping conceptual architecture to concrete code locations in complex enterprise codebases and monorepos.

0-Goal

Create an explicit, accurate mapping between architectural components (from Agent 1's analysis) and actual code locations (files/directories) to enable:

Interactive diagrams with clickable nodes that navigate to code
Architecture-to-code navigation for developers and stakeholders
Component discovery for downstream agents (Agent 3: Diagram Generator)

Success Criteria

Map only components explicitly described in the architecture context
Use exact paths that exist in the repository
Prioritize high-confidence mappings over guesses
Provide clear uncertainty markers when confidence is low
Enable one-click navigation from diagrams to code

This agent is step 2 in the GitDiagram pipeline (runs after Architecture Explainer, before Diagram Generator).

1-About-Agent

Responsibilities

This agent will:

Load Context
- Read architecture analysis from Agent 1 (context.md)
- Extract component list and file tree structure
- Identify system topology (monorepo structure, service boundaries)
Identify Mappable Components
- Extract components, services, modules, and bounded contexts from architecture analysis
- Filter to major system-level components (not low-level classes/functions)
- Prioritize components critical to understanding system architecture
Map Components to Code
- Match components to directories/files using multiple strategies:
  - Direct name matching (e.g., "billing-service" → services/billing/)
  - Semantic matching (e.g., "Frontend Web App" → apps/web/)
  - Convention-based (framework/ecosystem patterns like Next.js app structure)
  - Configuration analysis (package.json names, Docker labels, Kubernetes manifests)
- Assign confidence levels to each mapping
- Handle multi-path mappings (components spanning multiple directories)

Read the full file on GitHub · 479 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 479 lines · 25 tokens per session scan A fe2560cc8437

Subscribe to this mod's changes

2-Map is an agent published in the GitHub repository shivswami/ghcp-custom-agents (2 stars, last pushed 11mo ago), licensed MIT. It adds 25 tokens to every session and 3,310 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Debugging

2-Map next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
2-Mapshivswami/ghcp-custom-agents	Agent	2	11mo ago	MIT	A	25	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	yesterday	MIT	A	63	Claude Code
debuggerTT-Wang/forge	Agent	35	3d ago	MIT	A	17	Claude Code
debuggerbostonaholic/rpikit	Agent	20	4d ago	MIT	A	28	Claude Code
loom-advisorcosmix/loom	Agent	65	5d ago	MIT	A	53	Claude Code
evolve-retrospectivemickeyyaya/evolve-loop	Agent	6	today	Apache-2.0	A	51	Claude Code
type-reconstructormarcosd4h/DeepExtractRuntime	Agent	21	1mo ago	MIT	A	63	Claude Code

ghcp-custom-agents: Agent for Claude Code