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 skills/dojogenesis/mcp/codebase-viewernpx skills add DojoGenesis/mcp --skill codebase-viewergit clone --depth 1 https://github.com/DojoGenesis/mcpWhat 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 | $0.00034 | $0.00720 |
| Opus 5 | $0.00017 | $0.00360 |
| Sonnet 5 | $0.00007 | $0.00144 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade A, and why
codebase-viewer 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 yesterday.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Viewer
Produces a structured codebase map — not a file listing but an annotated architecture view with entry points, dependency flow, test coverage, and danger zones.
Workflow
1. TREE
Generate directory structure (2-3 levels deep) with role annotations:
- Each directory gets a one-line role description
- Mark directories as: source, test, config, docs, build, generated, vendored
- Flag empty directories and their likely purpose
- Respect .gitignore — skip node_modules, vendor, build outputs
2. ENTRY
Identify entry points — where execution begins:
mainfunctions (Go, Rust, Python)- CLI command handlers
- HTTP route registrations
- Event listeners and subscribers
- Scheduled task definitions
- Test suites (as secondary entry points)
3. DEPS
Map the dependency graph:
- External dependencies from go.mod / package.json / Cargo.toml / requirements.txt
- Internal package import relationships
- Circular dependency detection
- Heavyweight dependencies (large transitive dep trees)
4. TESTS
Scan for test coverage:
- Which packages/directories have test files
- Test-to-source ratio per directory
- Packages with zero tests (flag as risk)
- Test patterns in use (unit, integration, e2e, benchmark)
5. PATTERNS
Identify architectural patterns:
- Clean architecture / hexagonal / onion (ports-and-adapters)
- MVC / MVVM
- Microservice boundaries
- Monolith with internal module separation
- Event-driven / message-passing
- Repository pattern / service layer
6. DRAGONS
Flag areas of concern — severity-labeled:
- CRITICAL: Files >1000 lines, circular dependencies, hardcoded secrets
- WARNING: Files >500 lines, deeply nested code (>4 levels), TODO/FIXME density >5 per file
- INFO: No tests for package, outdated dependencies, unused imports
7. CONTRACTS
Identify interfaces and API boundaries:
- Go interfaces and their implementors
- HTTP API surface (routes, methods, request/response types)
- gRPC / protobuf definitions
- Event schemas
- Configuration contracts (env vars, config files)
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.
- yesterday First seen · 90 lines · 34 tokens per session scan A fd252bb1ba6d
codebase-viewer is a skill published in the GitHub repository DojoGenesis/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 720 once invoked, about $0.0002 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 skills, from other repositories
migrate-goldmark-extension-v1-to-v2
Migrate goldmark extension from goldmark v1 to v2.
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
sq-actions-dependabot
Reviews and merges Dependabot pull requests for GitHub Actions (the github-actions ecosystem) that bump uses: pins in .github/workflows/. Use for Dependabot githubactions PRs (branches like dependabot/githubactions/...), not go.mod or site/ Bun PRs.
jwx-companion-bulk
Apply bulk operations across all jwx companion modules. Args.
readme-generate
從原始碼分析自動生成雙語 README。當使用者請求為專案建立 README、需要從程式碼庫生成 README.md（英文）和 README.zh.md（中文）、或希望為其函式庫/套件建立一致的多語言文件時使用。.
gograph
Go repository intelligence for Claude Code. Use when reading, navigating, editing, reviewing, or refactoring a Go codebase. Exposes 64 query, analysis, and workflow capabilities through the local gograph MCP server, including bounded first-call exploration, AST-aware call graphs, blast-radius analysis, impact, and…