choiyounggi

choiyounggi/dev-loop

Plugin Claude Code

Marketplace for dev-loop — a wiki-grounded implementation loop plugin for Claude Code (loop-orchestrator + dev-llm-wiki, merged).

choiyounggi/dev-loop

Plugin Claude Code

loop-orchestrator's verification loop (TDD / PDCA / Reflexion) with the plan step FIXED to a wiki-grounded planning methodology (wiki-plan): every design decision is routed to a bundled semantic-layer wiki before code is written. Adds a knowledge-capture loop — sessions emit verified insights, and knowledge-flush…

choiyounggi/dev-loop

Instructions file CodexOpenCode

Instructions for choiyounggi/dev-loop, covering dev-llm-wiki — agent schema, what this wiki is, directory layout, routing protocol (how to consume) and page format (how to write).

choiyounggi/dev-loop

Agent

Read-only fresh-context reviewer for the merged integration diff across all tasks in an orchestration run. Invoked at Phase 5 so the coordinator's own degraded peak context never has to hold the full integration diff. Returns a fixed VERDICT and FINDINGS.

choiyounggi/dev-loop

Agent

Read-only verifier that audits one task's diff and tests for quality. Invoked between self-review and done so the session that wrote the code does not grade its own tests (self-grading guard). Returns a fixed VERDICT and REASONS.

choiyounggi/dev-loop

Hook

Runs when a session starts on startup, executing preflight.sh, insight-instruction.sh and config-nudge.sh via bash (3 commands). From choiyounggi/dev-loop.

choiyounggi/dev-loop

Hook

Runs before the agent uses a tool for Bash tool calls, executing pre-flush-pr-gate.sh and orchestrate-ask-gate.sh via bash (2 commands). From choiyounggi/dev-loop.

choiyounggi/dev-loop

Hook

Runs when the agent finishes a response, executing loop-gate.sh, harvest-insights.sh and auto-flush.sh via bash (3 commands). From choiyounggi/dev-loop.

choiyounggi/dev-loop

Skill Claude CodeCodex

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

choiyounggi/dev-loop

Skill Claude CodeCodex

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), runs wiki-ingest, then…

choiyounggi/dev-loop

Skill Claude CodeCodex

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 reflects and retries…

choiyounggi/dev-loop

Skill Claude CodeCodex

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 task, use…

choiyounggi/dev-loop

Skill Claude CodeCodex

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.

choiyounggi/dev-loop

Skill Claude CodeCodex

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

choiyounggi/dev-loop

Skill Claude CodeCodex

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.

choiyounggi/dev-loop

Skill Claude CodeCodex

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.

choiyounggi/groundwork

Plugin Claude Code

A safe-by-default, batteries-included Claude Code harness starter pack — guardrails, a wiki-grounded quality loop, and a memory lifecycle.

choiyounggi/groundwork

Plugin Claude Code

Safe-by-default guardrails for Claude Code: a PreToolUse Bash guard that blocks supply-chain / disk-destroying / fork-bomb commands and asks before rm -rf, force-push, DROP/TRUNCATE, kubectl delete, secret/credential access, and cloud-resource deletion — every rule configurable (off / ask / block) — plus a redacted…

choiyounggi/groundwork

Hook

Runs before the agent uses a tool for Bash tool calls, executing bash-guard.sh via bash. From choiyounggi/groundwork.

choiyounggi/groundwork

Hook

Runs after a tool call finishes for Bash and mcp__.* tool calls, executing audit-log.sh via bash. From choiyounggi/groundwork.

choiyounggi/groundwork

Skill Claude CodeCodex

Prove the guardrails Bash guard is live — runs a simulation that feeds representative dangerous commands (curl|sh, rm -rf, DROP TABLE, kubectl delete, cloud deletes, …) through the real guard and shows the block/ask decision for each, WITHOUT executing any of them. Use when asked to verify the guard is working, or…

choiyounggi/groundwork

Plugin Claude Code

A memory lifecycle for Claude Code's native file-based memory: a save gate against hallucinated memories, tiered expiry (short-tier memories archived — never deleted — when they lapse), a propose-then-confirm consolidation pass (merge/dedupe long-tier memory), a periodic learning-review nudge, a two-file habit frame…

choiyounggi/groundwork

Skill Claude CodeCodex

Periodically merge the memory index and long-tier memory files — deduplicate, resolve contradictions to the current truth, absolutize dates — and propose the result for your confirmation before any write. Use when MEMORY.md grows large (120+ lines) or long-tier memories accumulate duplicates, contradictions, or stale…

choiyounggi/groundwork

Skill Claude CodeCodex

Distill a lesson — a mistake, a user correction, or a praised behavior — into HABITS.md as a positive practice or a hard line. Use after the user corrects you, after an incident, or when the learning-nudge hook fires.