dev-loop

Plugin dev-loop from marketplace buildwithclaude in davepoon/buildwithclaude. Commands read from the repo's manifest — yesterday.

Skills (9)

• configure

  Set up dev-loop's capability-role tool profile — map `knowledge` (your domain wiki / MCP), `verify` (your project's test/build/lint/typecheck/QA command), `explore` (code search), `tacit` (past incidents), and `design` (Figma/visual spec) to the actual tools this environment has, then write ~/.claud

• graph-setup

  Onboard a workspace of git repos onto the graphify code graph — detect or (with consent) install graphify, record the workspace roots in tools.json, build absent graphs with graphify update after one batch confirmation, and install graphify's post-commit/post-checkout hooks plus dev-loop's post-merg

• knowledge-flush

  Drain queued ★ Insight candidates (harvested from your sessions) into the wiki as a reviewed PR. For each candidate it researches and verifies the best-practice against real sources, checks existing wiki layers for duplicates and links, decides the target layer/category (or justifies a new one), run

• loop-implement

  The single implementation loop. It plans via wiki-plan (step 2, required) into an ordered, wiki-navigated task list, then executes those tasks in order, each loading only its named wiki pages, writing tests first, getting an independent test-quality audit, and judging against done; on failure it ref

• orchestrate

  Orchestrate one natural-language goal into parallel tmux Claude Code sessions. It decomposes the goal (with your approval), plans each task with wiki-plan, implements and reviews, runs an integration test, and merges after your confirmation. Use to build a goal across multiple sessions. For a single

• wiki-ingest

  Add one verified lesson or edge case to the bundled wiki. Route it to the right domain and category, merge into an existing page before creating a new one, and enforce sourcing and positive-guidance rules. Use when capturing a documented best practice or a production edge case.

• wiki-lint

  Health-check the bundled wiki. Detect unsourced claims, bare prohibitions, broken links, index and page trigger mismatches, vague qualifiers, oversized pages, stale dates, and model-era re-verification candidates, then fix them; reports a numeric health score (0-100). Use to keep the wiki healthy be

• wiki-plan

  The fixed planning methodology for a capable model. Make every design decision grounded in a bundled wiki page (recording a decision-to-page map), then decompose the work into ordered, self-contained tasks, each naming the exact wiki pages that govern it. Runs as loop-implement step 2.

• wiki-query

  Answer a development question from the wiki with citations, loading only the pages whose triggers match. If the answer required synthesis across multiple pages and the question is likely to recur, file the synthesis back as a new page so knowledge compounds.

Subagents (11)

• integration-reviewer-r1

  R1/R0 tier copy (one effort step lower, never below high) of the integration-reviewer agent. Read-only for repo state (no commits, no source edits that survive) fresh-context reviewer for the merged integration diff across all tasks in an orchestration run — running checks may temporarily mutate the

• integration-reviewer

  Read-only for repo state (no commits, no source edits that survive) fresh-context reviewer for the merged integration diff across all tasks in an orchestration run — running checks may temporarily mutate the working tree, always restored exactly. Invoked at Phase 5 so the coordinator's own degraded

• plan-reviewer

  Read-only fresh-context reviewer for a wiki-plan Phase B design (analysis.md + design doc). Returns a fixed VERDICT and FINDINGS.

• task-analyst-r1

  R1/R0 tier copy (one effort step lower, never below high) of the task-analyst agent. Fresh-context per-task analyst for an orchestration run — runs ONLY Phase A (Analyze) of the bundled wiki-plan skill for ONE task at Phase 3 step 2a, writes analysis.md and the gate-A ledger into the coordinator's c

• task-analyst

  Fresh-context per-task analyst for an orchestration run — runs ONLY Phase A (Analyze) of the bundled wiki-plan skill for ONE task at Phase 3 step 2a, writes analysis.md and the gate-A ledger into the coordinator's checkout, and replies with a fixed report. The task-planner agent then designs from th

• task-planner-r1

  R1/R0 tier copy (one effort step lower, never below high) of the task-planner agent. Fresh-context per-task planner for an orchestration run — runs Phase B (Design) and Phase C (Decompose) of the bundled wiki-plan skill for ONE task at Phase 3 step 2a, after the task-analyst agent wrote analysis.md;

• task-planner

  Fresh-context per-task planner for an orchestration run — runs Phase B (Design) and Phase C (Decompose) of the bundled wiki-plan skill for ONE task at Phase 3 step 2a, after the task-analyst agent wrote analysis.md; writes the plan artifacts and gate ledgers into the coordinator's checkout, and repl

• task-reviewer-r1

  R1/R0 tier copy (one effort step lower, never below high) of the task-reviewer agent. Read-only for repo state (no commits, no source edits that survive) fresh-context reviewer for ONE task's worktree diff in an orchestration run — running checks may temporarily mutate the working tree, always resto

• task-reviewer

  Read-only for repo state (no commits, no source edits that survive) fresh-context reviewer for ONE task's worktree diff in an orchestration run — running checks may temporarily mutate the working tree, always restored exactly. Invoked at Phase 4 so the coordinator never reads a per-task diff; writes

• test-quality-auditor-r1

  R1/R0 tier copy (one effort step lower, never below high) of the test-quality-auditor agent. Read-only for repo state (no commits, no source edits that survive) verifier that audits one task's diff and tests for quality — running the tests (step 4) DOES temporarily mutate the working tree, always re

• test-quality-auditor

  Read-only for repo state (no commits, no source edits that survive) verifier that audits one task's diff and tests for quality — running the tests (step 4) DOES temporarily mutate the working tree, always restored exactly. Invoked between self-review and done so the session that wrote the code does

MCP servers (1)

• dev-loop-wiki

  runs: bash ${CLAUDE_PLUGIN_ROOT}/scripts/wiki-mcp-launch.sh serve

Hooks (13)

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/preflight.sh"

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/insight-instruction.sh"

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/config-nudge.sh"

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/graph-nudge.sh"

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/wiki-index.sh"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/pre-flush-pr-gate.sh"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/orchestrate-ask-gate.sh"

• Stop

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/loop-gate.sh"

• Stop

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/harvest-insights.sh"

• Stop

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/auto-flush.sh"

• StopFailure

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/worker-blocked-signal.sh"

• Notification

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/worker-blocked-signal.sh"

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/worker-blocked-signal.sh"

Similar plugins