Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/shivswami/ghcp-custom-agents/2-mapgit clone --depth 1 https://github.com/shivswami/ghcp-custom-agentsWrote 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.
[](https://agentmods.dev/agents/shivswami/ghcp-custom-agents/2-map)<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="Measured on agentmods" height="20"></a>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 | $0.00025 | $0.03310 |
| Opus 5 | $0.00013 | $0.01655 |
| Sonnet 5 | $0.00005 | $0.00662 |
| Haiku 4.5 | $0.00003 | $0.00331 |
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 5d 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.
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)
- Read architecture analysis from Agent 1 (
-
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)
- Direct name matching (e.g., "billing-service" →
- Assign confidence levels to each mapping
- Handle multi-path mappings (components spanning multiple directories)
- Match components to directories/files using multiple strategies:
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.
- 5d ago First seen · 479 lines · 25 tokens per session scan A fe2560cc8437
2-Map is an agent published in the GitHub repository shivswami/ghcp-custom-agents (2 stars, last pushed 9mo ago), licensed MIT. It adds 25 tokens to every session and 3,310 once invoked, about $0.0001 per session on Opus 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.