claude-foundations/MEMORY.md

claude-foundations — Memory Index

Runbooks

• New ArgoCD App — Full procedure: manifests, KSOPS secrets, ArgoCD Application, Caddy reverse proxy, DNS, verification, common pitfalls

Scripts

• context-load — Walks cwd upward collecting CLAUDE.md, CONTEXT.md, MEMORY.md, BESTPRACTICES.md, trees, and git status for system prompt injection
• start-claude — Wrapper that runs context-load and launches claude with --append-system-prompt
• install-hooks — Symlinks hooks into ~/.claude/hooks/ and prints settings.json config
• setup-formatters — Opts a project into auto-formatting by symlinking formatter scripts
• git-status-report — Scans directories for git repos, reports uncommitted changes and remote sync (lives in small-scripts)
• statusline — Status bar scripts: statusline.sh (renderer) and set-topic.sh (topic setter) for per-session topic display
• require-plan-file — PreToolUse hook: blocks ExitPlanMode unless a *-PLAN.md file exists in the project root
• extract-transcripts — Manages transcript backup tracking: register, list, extract, mark-processed. Used by /log and pre-compact hook
• list-transcripts-here — Wrapper calling extract-transcripts.py --list $(pwd); exists to avoid $() in SKILL.md bang commands

Skills

• /end-session — End-of-session wrap-up: session log + CONTEXT.md update for seamless resumption
• /log — End-of-session logging to memory/log/ for later reflection
• /reflect-logs — Processes session logs into topic memory files (gotchas, decisions, process lessons)
• /reflect — Milestone reflection: reviews conversation + git log, produces structured artifacts
• /distill-best-practices — Cross-project distillation of memory files into best-practices/ topic files
• /linter — Audit and manage project formatters/linters (scan, run, cleanup modes)
• /context-load — Reload project context after /clear or mid-session context loss
• /housekeeping — Cross-project health check: git status, unreflected logs, skill validation, pipeline recommendations
• /decompose — Break tasks into subtasks with dependency graph, write .agent-tasks.json for container agent orchestration
• /orchestrate — Check task state, launch container agents in git worktrees. Use /loop 2m /orchestrate for auto-polling
• /review-plan — Review plan against best practices (API, security, specs, TDD) before implementation
• /review-spec — Review spec for structure, requirement quality, security coverage, and testability
• /spawn-session — Spawn a new detached tmux Claude Code session with Remote Control, named after a project (wraps claude-tmux)

References

• Infrastructure Docs Repo — Shared infrastructure catalog at ~/dev/claude/docs/infrastructure/homelab — system descriptions and dependency map for the homelab

Topic Files

• Decisions — Architecture and design decisions: pipeline design, linting system, context-load, CLAUDE.md structure
• Process Lessons — Working rules: git-status at session start, plan mode for architecture, hook exit codes, ssh-agent
• Gitea Gotchas — Push permission denied when repo created by different API user than SSH alias
• Skills Gotchas — Broken symlinks under set -e, mid-session skill discovery limitation, $() and $VAR bang-command rejection
• Statusline Gotchas — set-topic.sh bootstrap race condition, md5sum -n flag consistency
• Hooks Gotchas — PreCompact transcript_path removed from input; derive from session_id+cwd
• Python Gotchas — sys.exit() swallowed by bare except: inside loops