Archive228

Archive228/loopkit

Plugin Claude Code

Standalone marketplace for loopkit — 41 skills + minimal harness.

Archive228/loopkit

Plugin Claude Code

33 battle-tested skills + a minimal harness (CLAUDE.md, verifier subagent, format-on-write hook, MEMORY index, loop runner) for Claude Code, Cursor, Codex, and Gemini CLI.

Archive228/loopkit

Agent Claude Code

Reviews a diff against the goal spec assuming the code is broken. Invoke after every code change.

Archive228/loopkit

Command Claude Code

Draft suggested next features into featurelist.suggestions.json (separate from featurelist.json).

Archive228/loopkit

Command Claude Code

Run the batch quality pass over the current diff — simplify → reduce-nesting → kill-dead-code → a11y-pass → loading-empty-error-states → readme-audit.

Archive228/loopkit

Command Claude Code

Write the goal spec (PROMPT.md) before implementing. Loads the loopkit spec-first skill.

Archive228/loopkit

Command Claude Code

Run adversarial verification on the current diff before claiming done. Loads the loopkit adversarial-verify skill and dispatches the verifier subagent.

Archive228/loopkit

Hook Claude Code

Runs when a session starts on startup, clear and compact, running an inline shell check. From Archive228/loopkit.

Archive228/loopkit

Hook Claude Code

Runs before the context is compacted for manual and auto tool calls, running an inline shell check. From Archive228/loopkit.

Archive228/loopkit

Hook Claude Code

Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From Archive228/loopkit.

Archive228/loopkit

Settings file Claude Code

Agent settings declaring 1 hook event (PostToolUse) and 6 allowed tools.

Archive228/loopkit

MCP server Claude CodeCodexCursor +2

Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package. Needs 1 environment variable to run.

Archive228/loopkit

MCP server Claude CodeCodexCursor +2

Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.

Archive228/loopkit

Instructions file CodexOpenCode

AGENTS.md instructions for Archive228/loopkit, covering agents.md — loopkit loop contract, the three-step loop, single-feature rule, clean-state contract (end of every session) and skills vs rules.

Archive228/loopkit

Skill Claude CodeCodex

Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.

Archive228/loopkit

Skill Claude CodeCodex

Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt at session start — prose is for humans, JSON is for the loop.

Archive228/loopkit

Skill Claude CodeCodex

Review a diff against the goal spec assuming the code is BROKEN. The reviewer that lives in the maker's head always agrees with itself — this pulls review into a hostile, separate pass. Invoke after every code change before marking work done.

Archive228/loopkit

Skill Claude CodeCodex

Verify that an endpoint checks ownership, not just authentication. Use on any handler that reads or mutates user data.

Archive228/loopkit

Skill Claude CodeCodex

Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.

Archive228/loopkit

Skill Claude CodeCodex

Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything else. Kills the "looks shipped, isn't shipped" bug across sessions.

Archive228/loopkit

Skill Claude CodeCodex

Turn a set of commits or a diff into a clean, user-facing changelog entry. Use before a release or PR description.

Archive228/loopkit

Skill Claude CodeCodex

Turn messy WIP into clean, atomic commits with messages that explain why. Use before opening a PR.

Archive228/loopkit

Skill Claude CodeCodex

Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.

Archive228/loopkit

Skill Claude CodeCodex

Test the boundary between two systems by the contract, not the implementation. Use for APIs, integrations, and shared interfaces.