jl-cmd

jl-cmd/claude-dream

Plugin Claude Code

Plugin marketplace listing 1 plugin: dream.

jl-cmd/claude-dream

Plugin Claude Code

Memory consolidation for Claude Code. Simulates the Auto Dream feature by auditing, deduplicating, and rebuilding your memory files.

jl-cmd/claude-dream

Instructions file GitHub Copilot

Instructions for jl-cmd/claude-dream, covering code rules, comments, naming, magic values & configuration and types.

jl-cmd/claude-dream

Skill Claude CodeCodex

Consolidate, prune, and reorganize auto memory files. Simulates Auto Dream -- fixes format drift, deduplicates facts, enforces index structure. Use when memory feels stale or cluttered. Triggers on '/dream', 'consolidate memory', 'clean up memory', 'dream'.

jl-cmd/claude-dev-env

Plugin Claude Code

Plugin marketplace listing 1 plugin: config.

jl-cmd/claude-dev-env

Plugin Claude Code

Code standards, rules, hooks, agents, and commands for consistent Claude Code development across repos.

jl-cmd/claude-dev-env

Hook Claude Code

Runs when a session starts on startup and resume, executing python_script_launcher.js via node. From jl-cmd/claude-dev-env.

jl-cmd/claude-dev-env

Settings file Claude Code

Agent settings declaring 1 hook event (SessionStart) and 4 allowed tools.

jl-cmd/claude-dev-env

Skill Claude CodeCodexCursor

Runs the pr-converge loop for jl-cmd/claude-dev-env using AHK auto-continue pacing. Activate when the user says "parallel-debug" or asks to run the pr-converge convergence loop in Cursor.

jl-cmd/claude-dev-env

Instructions file GitHub Copilot

Instructions for jl-cmd/claude-dev-env, covering copilot instructions, naming, comments and documentation, types and constants and configuration.

jl-cmd/claude-dev-env

Instructions file CodexOpenCode

Instructions for jl-cmd/claude-dev-env, covering agents.md, what this repo is, pii and secrets never enter this repo, commands and architecture.

jl-cmd/claude-dev-env

Instructions file

Instructions for jl-cmd/claude-dev-env.

jl-cmd/claude-dev-env

Agent Codex

Agent definition files installed into /.agents/agents/ by bin/install.mjs. /.claude/agents is a directory pointer to that folder. Each .md file defines a named subagent: its description (shown in the Claude Code UI), allowed tools, and behavioral instructions.

jl-cmd/claude-dev-env

Agent Codex

Use PROACTIVELY for ALL code generation — features, fixes, refactors, hooks, automation, and any task that produces code. Links the project review contract, CODERULES, enforcer, and rules map; task-local discovery; gotchas with clear checks and review evidence.

jl-cmd/claude-dev-env

Agent Codex

Use this agent for comprehensive code quality reviews across multiple files.

jl-cmd/claude-dev-env

Agent Codex

Use this agent when you need to create git commits, stage changes, or organize multiple file changes into atomic commits. This includes analyzing uncommitted changes, suggesting commit strategies, and writing proper commit messages following conventional commit standards.

jl-cmd/claude-dev-env

Agent Codex

Primary handler for one GitHub issue action per spawn on a work-stream: open an epic, file a sub-issue, update status in place, refresh the epic checklist, or close a sub-issue. Spawn with one action plus the issue-candidate or issue number it needs; loads the issue-tracker skill; returns affected issue numbers and…

jl-cmd/claude-dev-env

Agent Codex

Fresh-context validator for workflow-generated plan packets. Use after a plan packet is written under docs/plans/ / to verify source accuracy, completeness, TDD readiness, scope control, handoff quality, and no invented repo behavior. Read-only; never edits files.

jl-cmd/claude-dev-env

Agent Codex

Optional agent that drafts factual pull request descriptions and comments from the current diff and validates each statement against the master review guides.

jl-cmd/claude-dev-env

Agent Codex

Standing reviewer for a whole session, or for a shared session and the subagents it spawns. Consulted before committing to a multistep plan, once the session believes the work is complete, before any commit is executed, when the same failure repeats, or when reconsidering the chosen approach. Returns one of four…

jl-cmd/claude-dev-env

Agent Codex

Authors a skill package — SKILL.md plus companion files — to skill-builder conventions: hub layout, trigger-catalog description, deterministic work shipped as scripts and task-seed lists. Triggers: author a skill, write a SKILL.md, skill-writer-agent, delegate skill file authoring, produce skill package files.

jl-cmd/claude-dev-env

Skill Claude CodeCodex

Workflow-backed implementation planning that creates a deep repo-local packet under docs/plans/ / before any code changes. Use for /anthropic-plan, "plan this first", "think before coding", "make a plan", "scope this out", "don't code yet", and non-trivial implementation requests that need source-grounded design, TDD…

jl-cmd/claude-dev-env

Skill Claude CodeCodex

Audits a Claude Code setup (user CLAUDE.md, /.claude/rules/, project .claude/) for context-budget waste — duplicate @-imports, always-on rules to path-scope or convert to skills, oversized files — and produces a migration table with savings. Use when reviewing the startup/instruction load, when /memory shows…

jl-cmd/claude-dev-env

Skill Claude CodeCodex

Formats a reply as single-line beats in plain everyday words. Triggers: '/beat-sheet', 'beat sheet this', 'give me the beats', 'write this as beats', 'too long', 'shorter', 'what?', 'english', 'no sense', 'jargon', 'huh?'.