create-beads-orchestra…
Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing…
Invoke at the start of any implementation task to enforce verification-first development
$ npx -y skills add avivk5498/the-claude-protocol --skill subagents-discipline --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/subagents-disciplineContext preview
The summary Claude sees to decide when to auto-load this skill.
Invoke at the start of any implementation task to enforce verification-first development
name: subagents-discipline description: Invoke at the start of any implementation task to enforce verification-first development
**Core principle:** Test the FEATURE, not just the component you built.
---
Before writing code that touches external data (API, database, file, config):
1. **Fetch/read the ACTUAL data** - run the command, see the output 2. **Note exact field names, types, formats** - not what docs say, what you SEE 3. **Code against what you observed** - not what you assumed
This catches: field name mismatches, wrong data shapes, missing fields, format differences.
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
Both are required. Component test alone is NOT sufficient.
| 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 |
**The pattern:** 1. Build the thing 2. Component test - verify your piece works in isolation 3. Feature test - verify the integrated feature works end-to-end 4. Only then claim done
Before claiming you can't fully test:
1. **Check what MCP servers you have access to** - list available tools 2. **If any tool can help verify the feature works**, use it 3. **Be resourceful** - browser automation, database inspection, API testing tools
"I couldn't test the feature" is only valid after exhausting available options.
---
Every completion must include evidence. Code reviewer will verify this.
DEMO:
COMPONENT:
Command: [what you ran to test the component]
Result: [what you observed]
FEATURE:
Steps: [how you tested the integrated feature]
Result: [what you observed - screenshot, output, etc.]If you genuinely cannot test end-to-end (long-running job, external service, no browser tools):
DEMO:
COMPONENT:
Command: curl localhost:3008/api/endpoint
Result: 200, returns expected data
FEATURE: PARTIAL
Verified: [what you could test]
Needs human check: [what still needs verification]
Why: [specific reason - no browser MCP, takes 10+ minutes, requires external service]**Not acceptable reasons for PARTIAL:**
**Acceptable reasons:**
---
If your BEAD_ID contains a dot (e.g., BD-001.2), you're implementing part of a larger feature:
1. **Check for design doc**: `bd show {EPIC_ID} --json | jq -r '.[0].design'` 2. **Read it if it exists** - this is your contract 3. **Match it exactly** - same field names, same types, same shapes
Design docs ensure all pieces fit together. If you deviate, integration fails.
---
Before marking done:
---
When you catch yourself thinking:
When you're about to say:
---
Component test passing ≠ feature works Curl returning 200 ≠ UI displays correctly TypeScript compiles ≠ user can use it
Test the feature like a user would use it. Then show evidence. Then claim done.
Enforcement-first orchestration for Claude Code. Every agent tracked. Every decision logged. Nothing gets lost. Claude Code plans great. Without structure, nothing survives past one session. macOS and Linux.
Repo: avivk5498/the-claude-protocol
Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing…
React and Next.js performance optimization patterns. Use BEFORE implementing any React code…