Instructions file CodexOpenCode
AGENTS.md instructions for haacked/dotfiles, covering dotfiles project and shell configuration.
Instructions file CodexOpenCode
AGENTS.md instructions for haacked/dotfiles, covering dotfiles project and shell configuration.
Instructions file
Claude Code instructions for haacked/dotfiles, a project described as: My dotfiles and scripts I use on dev machines.
Agent
Assesses whether it is safe to approve the gated CI workflows on an outside-contributor (fork) pull request. GitHub holds a fork PR's workflows until a maintainer clicks "Approve and run", because approval lets the contributor's code execute in CI with access to the base repo's runners and secrets. This agent reads…
Agent
Use this agent when you encounter a failing test, unexpected behavior, or need to investigate the underlying cause of a software defect. Examples: Context: User is debugging a failing integration test that worked yesterday but now fails intermittently. user: "This test keeps failing randomly - sometimes it passes…
Agent
Reviews code for bugs, logic errors, security vulnerabilities, and project guideline violations. Does not cover readability or refactoring (use the simplify skill for that). Examples: before committing changes, after implementing a new feature, or when you want a correctness check.
Agent
Use this agent when you need to break down complex software features or requirements into actionable implementation stages, create technical specifications, or design system architecture before coding begins. Examples: Context: User wants to add a new authentication system to their web application. user: 'I need to…
Agent
Investigates a single operational hypothesis using production metrics, logs, dashboards, and PostHog product data (Grafana/Prometheus/Loki/PostHog DB/PostHog data warehouse). Spawn one instance per hypothesis so the orchestrator can fan out in parallel. Use when the question is answered by observability data, not…
Agent
Use this agent when you need to capture and organize complex technical discoveries, debugging findings, or system knowledge for future reference. Specifically triggered when you've completed extensive exploration of software systems, discovered non-obvious behaviors, or solved complex technical problems that should be…
Agent
Use this agent when you need to improve, refine, or optimize prompts for AI systems, LLMs, or other automated tools. Examples include: refining system prompts for better performance, analyzing prompt effectiveness, restructuring prompts for clarity and precision, optimizing prompts for specific use cases or domains…
Agent
Triages a single CI flake (a failing test or a flaky infra step) and, if it looks like a genuine unknown flake, reports it to the @PostHog bot in the #flakey-tests Slack channel so the bot can investigate. Fire-and-forget: spawn it with a failing job URL and keep working. It does NOT root-cause, fix, or reproduce the…
Agent
Use this agent when providing customer support that requires technical problem-solving and debugging. Examples: Context: User is helping a customer who reported that their API integration is failing with 401 errors. user: 'Customer is getting 401 errors when calling our API, they say their API key is correct'…
Agent
Use this agent to determine the optimal agent workflow for development tasks. It analyzes task complexity and recommends which agents to use and in what sequence. Examples: Context: User has a complex feature request but isn't sure how to approach it. user: 'I need to add real-time notifications to my app with email…
Agent
Analyzes GitHub issues and PRs (external and internal) to identify those belonging to the Feature Flags team domain (feature flags, cohorts, early access). Used by the triage-issues command.
Agent
Use this agent when you need to write comprehensive unit tests for existing code, when implementing test-driven development, when code coverage needs improvement, or when refactoring requires test safety nets. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this…
Skill Claude CodeCodex
Simplify recently changed code for clarity, consistency, and maintainability while preserving behavior. Use after implementation or when asked to simplify or refactor code without changing what it does.
Skill Claude CodeCodex
Evaluate unresolved PR review comments from any reviewer — bots and humans — fix legitimate issues, and reply to dismissed ones.
Skill Claude CodeCodex
Analyze accumulated permissions and suggest smart wildcard patterns. Only invoke when the user explicitly runs /analyze-permissions or asks to analyze their Claude Code permissions.
Skill Claude CodeCodex
One sweep over all of my open PRs — check CI and merge-queue state, handle new review comments, fix and push — tracking state so reruns skip already-handled work. Designed to be driven by /loop.
Skill Claude CodeCodex
Monitor CI checks after pushing, detect flaky vs legit failures, and auto-fix. Follows a PR into a Trunk merge queue, where the queue's CI runs on its own branch.
Skill Claude CodeCodex
Delete and tighten code comments in source files after they are written. Drops narration, restatement, and change-log comments, then cuts the survivors to one fact each. Use when the user says the comments are too wordy, asks to clean up or trim comments, or right after generating code that came out over-commented.…
Skill Claude CodeCodex
Commit staged/unstaged changes with a well-crafted commit message.
Skill Claude CodeCodex
Create or update a GitHub PR with automatic template detection and filling, enforcing a plain staff-engineer writing voice in the PR body.
Skill Claude CodeCodex
Explain each open or skipped code-review item in plain English, weigh what happens on each side of the decision, and give a recommendation.
Skill Claude CodeCodex
Capture a follow-up item mid-session in seconds, list open items, close one, or run a review pass. Use when the user says "follow up on this later", "add a followup", "don't let me forget", or runs /followup.