Discover Codebase Enhancements
Overview
Spend significant time crawling and analyzing the codebase to surface high-impact improvements. Center findings on the jobs-to-be-done of the codebase, developers, end users, and AI agents working in the repo.
Inputs (ask if missing, max 5)
- Target area or scope (whole repo or specific modules)
- Primary user jobs-to-be-done and business goals
- Known pain points or incidents
- Constraints (time, risk tolerance, release window)
- Evidence sources allowed (tests, metrics, logs)
Jobs-to-Be-Done Lens
- Codebase: reliability, simplicity, maintainability
- Developers: speed, clarity, safe changes
- End users: correctness, performance, usability
- AI agents: discoverability, consistency, explicit patterns
Workflow
- Deep crawl
- Read architecture docs, READMEs, key modules, and tests.
- Search for hotspots (TODO/FIXME, large files, duplication, complex flows).
- Evidence gathering
- Note error-prone areas, missing tests, performance risks, and coupling.
- Capture references to files/functions and concrete symptoms.
- Opportunity synthesis
- Group findings by theme: correctness, performance, DX, architecture, tests, tooling.
- Impact scoring
- Rate impact, effort, risk, and evidence strength.
- Ranked recommendations
- Present top enhancements with rationale and expected outcomes.
Output Format
## Codebase Enhancement Discovery
### Context Summary
[1-3 sentences]
### JTBD Summary
- Codebase: ...
- Developers: ...
- End users: ...
- AI agents: ...
### Evidence Sources
- Files/modules reviewed: ...
- Patterns searched: ...
- Tests or metrics considered: ...
### Ranked Enhancements
1) [Enhancement]
- Category: ...
- Impact: high | Effort: medium | Risk: low | Evidence: moderate
- Rationale: ...
- Affected areas: ...
### Quick Wins
- ...
### Open Questions
- ...
Quick Reference
- Spend more time exploring than feels necessary.
- Prefer evidence-backed findings over speculation.
- Center recommendations on user and developer outcomes.
Common Mistakes
- Skimming without enough code context
- Listing fixes without evidence or impact scoring
- Ignoring AI agent or developer workflows
- Recommending changes that fight existing architecture
1---2name: discover-codebase-enhancements3description: Use when the user asks for a deep codebase analysis to identify and rank improvements, optimizations, architectural enhancements, or potential bugs aligned to developer, end-user, and agent jobs-to-be-done.4---5
6# Discover Codebase Enhancements
7
8## Overview
9Spend significant time crawling and analyzing the codebase to surface high-impact improvements. Center findings on the jobs-to-be-done of the codebase, developers, end users, and AI agents working in the repo.
10
11## Inputs (ask if missing, max 5)
12- Target area or scope (whole repo or specific modules)
13- Primary user jobs-to-be-done and business goals
14- Known pain points or incidents
15- Constraints (time, risk tolerance, release window)
16- Evidence sources allowed (tests, metrics, logs)
17
18## Jobs-to-Be-Done Lens
19- **Codebase**: reliability, simplicity, maintainability
20- **Developers**: speed, clarity, safe changes
21- **End users**: correctness, performance, usability
22- **AI agents**: discoverability, consistency, explicit patterns
23
24## Workflow
251. **Deep crawl**
26 - Read architecture docs, READMEs, key modules, and tests.
27 - Search for hotspots (TODO/FIXME, large files, duplication, complex flows).
282. **Evidence gathering**
29 - Note error-prone areas, missing tests, performance risks, and coupling.
30 - Capture references to files/functions and concrete symptoms.
313. **Opportunity synthesis**
32 - Group findings by theme: correctness, performance, DX, architecture, tests, tooling.
334. **Impact scoring**
34 - Rate impact, effort, risk, and evidence strength.
355. **Ranked recommendations**
36 - Present top enhancements with rationale and expected outcomes.
37
38## Output Format
39```
40## Codebase Enhancement Discovery
41
42### Context Summary
43[1-3 sentences]
44
45### JTBD Summary
46- Codebase: ...
47- Developers: ...
48- End users: ...
49- AI agents: ...
50
51### Evidence Sources
52- Files/modules reviewed: ...
53- Patterns searched: ...
54- Tests or metrics considered: ...
55
56### Ranked Enhancements
571) [Enhancement]
58 - Category: ...
59 - Impact: high | Effort: medium | Risk: low | Evidence: moderate
60 - Rationale: ...
61 - Affected areas: ...
62
63### Quick Wins
64- ...
65
66### Open Questions
67- ...
68```
69
70## Quick Reference
71- Spend more time exploring than feels necessary.
72- Prefer evidence-backed findings over speculation.
73- Center recommendations on user and developer outcomes.
74
75## Common Mistakes
76- Skimming without enough code context
77- Listing fixes without evidence or impact scoring
78- Ignoring AI agent or developer workflows
79- Recommending changes that fight existing architecture
tools-only