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/saitarrun/devforge-ai/codebase-navigatornpx skills add saitarrun/Devforge-ai --skill codebase-navigatorgit clone --depth 1 https://github.com/saitarrun/Devforge-aiWhat 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 | $0.00033 | $0.00763 |
| Opus 5 | $0.00016 | $0.00381 |
| Sonnet 5 | $0.00007 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
codebase-navigator 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 2d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Large-Scale Codebase Navigation & Comprehension Skill
This skill defines standard methodology for navigating, mapping, and understanding massive enterprise repositories, microservices, and monorepos (e.g., Turborepo, Nx, Lerna, Go workspaces, multi-package repositories).
1. Multi-Tier Exploration Strategy
When exploring an unfamiliar or massive codebase, never blindly read random files. Follow this 4-tier navigation sequence:
[Tier 1: Architectural Topography]
→ Package manifests (package.json, go.mod, Cargo.toml, pyproject.toml)
→ Workspaces / Monorepo layout
→ Domain Context (CONTEXT.md, README.md, docs/adr/)
↓
[Tier 2: Structural Knowledge Graph (code-review-graph)]
→ Submodule / Service boundary dependency map
→ Module coupling & circular dependency detection
↓
[Tier 3: Symbol & Call-Graph Tracing]
→ Entrypoints (routes, CLI commands, queue consumers, gRPC handlers)
→ Caller / Callee hierarchy for critical abstractions
↓
[Tier 4: Precision Target Inspection]
→ Focused file/function reading with bounded context
2. Structural Querying Priority
Always query code semantics rather than relying on noisy keyword matching:
| Priority | Tool / Mechanism | Best Used For |
|---|---|---|
| 1. Primary | code-review-graph / LSP AST |
Understanding symbol definitions, call hierarchies, cross-module couplings, and change impact |
| 2. Secondary | Ripgrep / Structural Grep | Fast discovery of specific error strings, environment variables, config keys, or regex tokens |
| 3. Fallback | Glob / Directory Traversal | Mapping tree hierarchy when building high-level system mental models |
3. High-Leverage Navigation Patterns
Pattern A: Tracing Ingress-to-Egress Dataflows
When tracking an end-to-end user action in a complex repo:
- Locate Ingress: Identify API route handler or message queue listener (
/api/v1/...,@Post(),def handle_event). - Trace Service Layer: Inspect domain service orchestration logic and business validation rules.
- Trace Persistence Layer: Examine database repository, ORM queries, and transaction boundaries.
- Inspect Egress Side-Effects: Check emitted events (Kafka/RabbitMQ), outbound webhooks, or cache invalidation calls.
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.
- 2d ago First seen · 75 lines · 33 tokens per session scan A 1759b696240a
codebase-navigator is a skill published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 33 tokens to every session and 763 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
skill-code-quality
This skill should be used when implementing code quality standards, setting up linting/testing/security scans, enforcing coverage thresholds, or establishing CI/CD guardrails.
improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
skill-developer-relations
SDK development, external developer communication, code samples, API client libraries, community engagement, and developer experience. Use when creating SDKs, writing external guides, creating code samples, or improving developer experience.
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
skill-architecture
This skill should be used when the user asks to "design a system", "architecture", "ADR", "system design", "tech stack", "choose between approaches", "coupling", "service granularity", "blueprint", "component design", "API contract", "schema design", "trade-offs", or discusses "monolith", "microservices", "fitness…
skill-accessibility
WCAG 2.1 AA compliance, keyboard navigation, screen reader testing, semantic HTML, ARIA labels, color contrast, assistive technology validation. Use when ensuring accessibility, conducting a11y audits, testing with screen readers, or designing inclusive interfaces.