with one click
subagents-discipline
Core engineering principles for implementation tasks
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Core engineering principles for implementation tasks
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | subagents-discipline |
| description | Core engineering principles for implementation tasks |
Before implementing anything, read the bead comments for investigation context:
bd show {BEAD_ID}
bd comments {BEAD_ID}
The orchestrator has already:
Use this context. Don't re-investigate. The comments contain everything you need to implement confidently.
If no investigation comments exist, ask the orchestrator to provide context before proceeding.
Before writing code that touches external data (API, database, file, config):
WITHOUT looking first:
Assumed: column is "reference_images"
Reality: column is "reference_image_url"
Result: Query fails
WITH looking first:
Ran: SELECT column_name FROM information_schema.columns WHERE table_name = 'assets';
Saw: reference_image_url
Coded against: reference_image_url
Result: Works
Component test catches: logic bugs, edge cases, type errors Feature test catches: integration bugs, auth issues, data flow problems
| You built | Component test | Feature test |
|---|---|---|
| API endpoint | curl returns 200 | UI calls API, displays result |
| Database change | Migration runs | App reads/writes correctly |
| Frontend component | Renders, no errors | User can see and interact |
| Full-stack feature | Each piece works alone | End-to-end flow works |
Before claiming you can't fully test:
If your BEAD_ID contains a dot (e.g., BD-001.2), you're implementing part of a larger feature:
bd show {EPIC_ID} --json | jq -r '.[0].design'When you catch yourself thinking:
Set up codebase intelligence for AI agents. Runs the agentifind CLI to extract code structure using LSP (pyright/tsserver) with tree-sitter fallback, then synthesizes a CODEBASE.md navigation guide. Run this skill to get a complete codebase map in .claude/ directory.
Create a benchmark to measure CODEBASE.md effectiveness. Sets up hooks to run two parallel agents (one with guide, one without) and compare their efficiency. Requires /agentifind to be run first.