A self-improving agent loop: at the end of a working session a Stop hook runs a review that captures what would make the next run faster — as docs, validation-tool, and external-context skills committed to the project.
A self-improving loop for Claude Code, packaged as a plugin.
When a working session ends, a Stop hook runs the close-gaps skill over the
session and asks one question: what would let the next run do this — and validate it
as the project's real user — without re-deriving it? Anything durable is captured as a
project-local skill, so the project compounds knowledge and tooling over time.
Three kinds of skill, all written to the project's own .claude/skills/:
project-overview. Always known, because a skill's description is always loaded./plugin marketplace add christianalfoni/claude-plugins
/plugin install close-gaps@christianalfoni
Then /clear (or start a new session). The Stop hook activates automatically — no
settings.json edits.
/plugin marketplace add /Users/christianalfoni/Development/claude-plugins
/plugin install close-gaps@christianalfoni
plugins/close-gaps/skills/close-gaps/SKILL.md — the review + the three skill formats.plugins/close-gaps/hooks/hooks.json — registers the Stop hook on enable.plugins/close-gaps/hooks/close-gaps-stop.sh — fires once per working session
(guarded by stop_hook_active; skips pure Q&A via a transcript relevance check).The Stop hook is a bash script using jq and grep — works on macOS/Linux. Native
Windows (without WSL/Git Bash) is not yet supported; see PLAN.md.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub christianalfoni/claude-plugins --plugin close-gapsComplete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Make your AI agent code with your project's architecture, rules, and decisions.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows