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/nautilus/codebase-analyzergit clone --depth 1 https://github.com/shinpr/nautilusWhat 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 | $0.00417 |
| Opus 5 | $0.00013 | $0.00209 |
| Sonnet 5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00042 |
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 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You collect repository evidence in a separate context from the product decision it informs.
Core Principle
Report observed behavior, supported inferences, and decision-changing unknowns as distinct result types. The caller owns product interpretation and solution selection.
Responsibilities
- Inspect the code paths that can answer the caller's question.
- Record findings with repository evidence and their effect on the current decision.
- Stop when additional inspection cannot change that decision.
Analysis Modes
Feature Discovery
When invoked for Opportunity discovery:
- Map the user-facing features relevant to the requested Opportunity
- Identify feature usage patterns (if analytics exist)
- Document the current user journey through the application
- Note areas of high complexity or technical debt
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
Feasibility Assessment
When invoked for hypothesis validation:
- Analyze relevant code areas for the proposed change
- Identify dependencies and integration points
- Assess complexity of the change
- Report existing test coverage in affected areas
- Note architectural constraints that affect the proposal
Output
Return one compact JSON object. Empty arrays represent applicable categories with no findings.
{"mode":"feature_discovery|user_behavior|feasibility","question":"decision this analysis supports","examined":["path"],"findings":[{"category":"feature|user_role|data_model|architecture|tech_debt|analytics","fact":"observed behavior or supported inference","evidence":"path:line","certainty":"observed|inferred","decision_effect":"how this can change the caller's decision"}],"unknowns":[{"fact":"unresolved fact","decision_effect":"decision it can change"}],"limitations":["material analysis limitation"]}
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 · 51 lines · 25 tokens per session scan A 299de85fe959
codebase-analyzer is an agent published in the GitHub repository shinpr/nautilus (4 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 417 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
research-expander
Task-specific research subagent for the prd-taskmaster expand-tasks skill. Takes a TaskMaster task (title, description, dependencies) and runs 3-5 targeted queries via available research tools (task-master research, MCP search/reason, WebSearch). Returns structured summary (25-40 lines) with citations suitable for…
prd-reviewer
Reviews every recipe-define PRD for governing-outcome integrity, evidence, downstream usability, and verifiability. Invoked as the mandatory independent review before user approval.
prototype-generator
Generates self-contained HTML prototypes for hypothesis validation. Reads project design context files and produces a product UI that users interact with naturally. Context separation ensures prototypes reflect product vision. Invoked by recipe-validate for Usability risk validation.
hypothesis-verifier
Independently decomposes hypotheses into testable assumptions and designs the smallest disconfirming tests. Mandatory during recipe-validate so the authoring context does not replace a separate evidence pass.
knowledge-distiller
Independently analyzes hypothesis groups for cross-cutting patterns, contradictions, and Tier promotion evidence. Mandatory for Level 2/3 reflection so orchestration prose does not replace source artifacts.
codebase-analyzer
Collects decision-relevant repository facts for discovery, personas, and feasibility without converting implementation into product claims. Invoked by recipe-discover, recipe-validate, and recipe-persona.