builder

Plugin builder from marketplace backend-agentic-marketplace in hafizmirhamza276-lab/backend-agentic-marketplace. Commands read from the repo's manifest — 1 month ago.

Skills (7)

• apply-change

  Implement an APPROVED plan (.claude/builder/PLAN.md) exactly as written — edit only the files listed in the plan's Scope, follow the conventions recorded in MEMORY.md, keep diffs minimal, and produce a change report. Use only after the orchestrator has rated the plan 9+/10 and validate-plan.sh has p

• diagnose-bug

  BUG-FIX MODE: turn a vague, repro-less bug report (e.g. 'the search field is not working', empty repro steps) into a verified, regression-safe fix via a deterministic symptom→reproduce→root-cause→characterize→fix→regression-gate workflow. Use when a spec is a bug report (auto-detected by a 'Bug:'/sy

• micro-decompose

  Decompose a requirement into the smallest INDEPENDENTLY-VERIFIABLE units, then harden each with an explicit edge-case enumeration drawn from a fixed taxonomy plus the codebase-specific risks in MEMORY.md. Use during planning (to write the PLAN.md '## Tasks' breakdown) and during implementation/QA (t

• plan-change

  Turn a spec (.claude/specs/specN.md) plus the explorer memory into (a) a clarity rating out of 10 and (b) a technical implementation plan that the orchestrator can rate. Use after recall-memory, before any code is written. Enforces evidence-first planning: every claim cites path:line, scope is an ex

• qa-verify

  Verify a freshly built feature with a hybrid strategy: auto-detect a real test/build harness and (with confirmation) run it for feature-level edge cases AND app-level regression; if no harness exists, fall back to rigorous static analysis and edge-case enumeration. Use after apply-change, before rep

• recall-memory

  Load the durable codebase memory written by the explorer plugin (.claude/explorer/MEMORY.md, index.json, TRACK.md, map/*.md) and turn it into a compact, build-ready context brief. Use this BEFORE planning or changing any code. Never re-scan the codebase when valid memory exists — recall is cheap, re

• sync-memory

  After a change is implemented and QA'd, update the durable memory so the next session is accurate: refresh the affected explorer artifacts (.claude/explorer/MEMORY.md, index.json, TRACK.md, map/*.md) and the builder log. Use as the final builder step. CRITICAL: resolve every index.json path on disk

Slash commands (2)

• /builder:start

  Spec-driven build. Reads the explorer memory as ground truth, plans a change from .claude/specs/, gates it (clarity 9+/10, technical plan 9+/10), implements only what the spec says, runs hybrid QA, then syncs the durable memory. Usage: /builder:start [optional note]

• /builder:status

  Show the current builder state cheaply — reads .claude/builder/ artifacts (PLAN.md, CHANGELOG.md, QA.md, settings.json) and explorer freshness, without spawning any sub-agents. Use to resume or inspect.

Subagents (8)

• builder-context-finder

  Read-only context loader for the builder flow. Recalls the explorer codebase memory (.claude/explorer/*) and produces a compact build-ready brief. Invoked first by /builder:start. Never scans the codebase from scratch and never edits anything.

• builder-diagnostician

  Critical-tier bug diagnostician for the builder flow (Opus 4.8, effort xhigh). Invoked by /builder:start in BUG-FIX MODE to run symptom intake → reproduce-first → root-cause → characterization (Phases B0–B3): writes the Bug Brief to .claude/builder/BUG.md, a FAILING reproduction test, characterizati

• builder-implementer

  Implements an APPROVED plan for the builder flow (Sonnet). Invoked by /builder:start only after the plan is rated 9+/10 and validate-plan.sh passes. Edits ONLY the files in the plan's Scope, follows MEMORY.md conventions, keeps diffs minimal, and writes a change report. The PreToolUse scope guard bl

• builder-memory-sync

  Final builder step (Sonnet): updates the durable memory so the next session is accurate — refreshes the affected explorer artifacts (MEMORY.md, index.json, TRACK.md, map/*.md) and the builder log. Invoked by /builder:start after QA passes. Resolves every index.json path on disk via find/glob (never

• builder-planner-deep

  Opus escalation planner for the builder flow. Invoked ONLY when the Sonnet planner has failed to produce a 9+/10 plan within the configured loop limit (default 2). Same job as builder-planner — recall context, read specs, rate clarity, write .claude/builder/PLAN.md — but with deeper reasoning. Token

• builder-planner

  Spec-driven planner for the builder flow (Sonnet). Reads the spec(s) in .claude/specs/ plus the explorer memory, rates clarity /10, and — only if clear enough — writes a technical implementation plan to .claude/builder/PLAN.md. Invoked by /builder:start after context is loaded. Does not write code.

• builder-qa-deep

  Opus escalation for QA in the builder flow. Invoked ONLY when the Sonnet QA agent failed to reach a 9+/10 result within the configured loop limit (default 2). Same hybrid method as builder-qa, with deeper edge-case and regression reasoning. Token-heavy; last resort, gated by settings.opus_escalation

• builder-qa

  Quality assurance for the builder flow (Sonnet). Invoked by /builder:start after implementation. Hybrid: auto-detects a test/build harness and (with confirmation) runs feature-level edge cases + app-level regression; if no harness, does rigorous static analysis. Writes a QA report and a confidence s

Hooks (8)

• SessionStart

  "${CLAUDE_PLUGIN_ROOT}"/scripts/check-builder-state.sh

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/guard-scope.sh

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/guard-bugfix.sh

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/guard-bash-write.sh

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}"/scripts/lint-feedback.sh

• SubagentStop

  "${CLAUDE_PLUGIN_ROOT}"/scripts/record-progress.sh

• Stop

  "${CLAUDE_PLUGIN_ROOT}"/scripts/verify-build.sh

• Stop

  "${CLAUDE_PLUGIN_ROOT}"/scripts/regression-gate.sh

Similar plugins