stilero

stilero/bankan

Hook Claude Code

Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing run-lint-on-edit.sh. From stilero/bankan.

stilero/bankan

Hook Claude Code

Runs when a task is marked completed, executing run-lint-on-task-complete.sh. From stilero/bankan.

stilero/bankan

Settings file Claude Code

Agent settings declaring 2 hook events (PostToolUse, TaskCompleted) and 4 allowed tools.

stilero/bankan

Instructions file CodexOpenCode

Instructions for stilero/bankan, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

stilero/bankan

Instructions file

Instructions for stilero/bankan, covering claude.md, what this is, commands, architecture and server modules (server/src/).

stilero/claude-plugins

Plugin Claude Code

Plugin marketplace listing 8 plugins: pr-comment-fixer, hardcore-code-reviewer, shopify-apps, github-issue-generator, obsidian-knowledge-bank.

stilero/claude-plugins

Instructions file

Claude Code instructions for stilero/claude-plugins, covering claude.md, what this is, repository structure, current plugins and plugin conventions.

stilero/claude-plugins

Plugin Claude Code

Almost-autonomous agent harness that takes a GitHub issue or Linear story through planning, review, implementation, hardcore code review, and draft-PR creation. Self-tunes its subagents via a meta-reflection loop within hard safety boundaries.

stilero/claude-plugins

Agent

Use when an agent-harness run needs to execute exactly one step from a PLAN.md. Examples.

stilero/claude-plugins

Agent

Use when the agent-harness needs to reflect on recent runs and propose (or apply) at most one improvement. Examples.

stilero/claude-plugins

Agent

Use when a PLAN.md has been drafted and needs a skeptical gap-finding pass before implementation begins. Examples.

stilero/claude-plugins

Agent

Use when an agent-harness run needs to turn a TASK.md brief into a step-by-step PLAN.md. Examples.

stilero/claude-plugins

Agent

Invoke the hardcore-code-reviewer skill on a worktree and return the verbatim report. Wraps the skill so the orchestrator can dispatch it via Task tool (clean return) instead of Skill tool (which stalls after long outputs).

stilero/claude-plugins

Agent

Use after the implementer finishes a single step to judge that step's diff. Examples.

stilero/claude-plugins

Command

Take a task (GitHub issue or Linear story) through planning, implementation, review, and draft PR. Usage: /agent-harness | # | .

stilero/claude-plugins

Command

Manually trigger a meta-reflection run. Usage: /agent-harness:reflect [--dry-run].

stilero/claude-plugins

Plugin Claude Code

Autonomous loop that fetches unresolved PR review threads, fixes them via pr-comment-fixer, hardens the diff via hardcore-code-reviewer, runs the host repo's resolved verification sequence, pushes, resolves threads, re-requests copilot review, and repeats until the PR is review-clean or hard caps trip.

stilero/claude-plugins

Command

Run the autonomous fix-pr-comments-loop on the current branch's PR (or a specified PR) until the reviewer signs off or hard caps trip.

stilero/claude-plugins

Skill Claude CodeCodex

Single-round executor for the fix-pr-comments-loop orchestrator. Runs steps 0–8 of one round (count unresolved threads, fix via pr-comment-fixer, harden via hardcore-code-reviewer, verify, push, resolve threads, re-request copilot, poll) in a fresh subagent context and returns a structured JSON result. Invoked once…

stilero/claude-plugins

Skill Claude CodeCodex

Autonomous loop that drives a pull request to a clean review state by dispatching one fresh Agent-tool subagent per round (each round = fetch unresolved copilot threads, fix via pr-comment-fixer, harden via hardcore-code-reviewer, verify, push, resolve threads, re-request copilot, poll). Per-round fresh context means…

stilero/claude-plugins

Plugin Claude Code

Evaluates findings and ideas from conversations and creates high-value GitHub issues. Checks for duplicates before creating, and updates existing issues with new findings instead of creating redundant ones.

stilero/claude-plugins

Command

Evaluate a finding or idea and create or update a GitHub issue if it's high value. Checks for duplicates first.

stilero/claude-plugins

Plugin Claude Code

Strict hardcore code reviewer that spawns 13 parallel subagents to review code from every angle: bugs, security, architecture, tests, error handling, performance, complexity, observability, API contracts, data/migrations, accessibility, type safety, and doc/comment drift.

stilero/claude-plugins

Agent

Reviews frontend code changes for accessibility violations including missing ARIA attributes, keyboard navigation gaps, screen reader issues, color contrast problems, and WCAG compliance failures. Spawned by hardcore-code-reviewer skill.