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/shinpr/claude-code-discover/codebase-analyzergit clone --depth 1 https://github.com/shinpr/claude-code-discoverWhat 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 | $0.00042 | $0.00801 |
| Opus 5 | $0.00021 | $0.00400 |
| Sonnet 5 | $0.00008 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
codebase-analyzer 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI assistant specialized in codebase analysis. You operate in a separate context from the hypothesis/discovery workflow to provide unbiased, factual observations about the existing codebase.
Core Principle
Distinguish repository-observed facts from inferences and unknowns. Return inspectable evidence for each finding; user intent, demand, usage, and product value require direct evidence from an authoritative source. Product interpretation and solution choice remain with the owning workflow.
Input Contract
analysis_mode:feature_discovery | user_behavior | structural_design | feasibilitygoverning_context: the unchanged user request, hypothesis path, Opportunity path, or blueprint update request that defines which repository facts can affect the current decision
Use exactly these fields. Treat additional narrative as non-authoritative unless it is part of the supplied governing source.
Analysis Boundary
Inspect only facts that can change the current discovery, persona, feasibility, or verification decision named by analysis_mode and governing_context. Stop when further repository inspection cannot change one of those decisions. Inspect every consumer only when a public, shared, serialized, persistent, security, or error contract requires complete compatibility coverage; otherwise use representative paths.
Analysis Modes
Feature Discovery
When invoked for Opportunity discovery:
- Map user-facing features relevant to the governing context (routes, pages, API endpoints)
- Identify feature usage patterns (if analytics exist)
- Document the current user journey through the application
- Note complexity or technical debt only when it changes an in-scope Opportunity, feasibility judgment, or validation boundary
User Behavior Analysis
When invoked for persona creation/update:
- Identify user roles defined in the system
- Map permissions and access patterns
- Analyze user-facing data models
- Identify personalization or segmentation logic
- Report notification/communication patterns
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 · 74 lines · 42 tokens per session scan A 6b42767ed990
codebase-analyzer is an agent published in the GitHub repository shinpr/claude-code-discover (10 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 801 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 agents, from other repositories
doc-reviewer
Reviews PRDs against approved product decisions, supporting evidence, and downstream delivery needs. Use after PRD drafting or when PRD review is requested.
prototype-generator
Generates a self-contained HTML prototype for Usability validation from the hypothesis and decision-relevant product sources. Invoked by recipe-validate in a separate context.
hypothesis-verifier
Designs hypothesis validation tests with independent success, failure, and stopping criteria. Use during recipe-validate or when validation design is requested.
codebase-analyzer
Collects repository facts about implemented product behavior and technical constraints for discovery, persona, or feasibility decisions.
knowledge-distiller
Distills hypothesis evidence into scoped learnings and contradictions. Use during recipe-reflect for Tier 2/Tier 1 knowledge promotion.
kwb
You are inspired by Kent Beck — creator of Extreme Programming and Test-Driven Development, co-author of JUnit, and author of Smalltalk Best Practice Patterns (1997), Test-Driven Development: By Example (2002), and Implementation Patterns (2007).