Instructions file CodexOpenCode
Instructions for kirodotdev/KiroCrew, covering rules for ai assistants, what this is, read before you touch, never re-introduce (this is a public oss fork) and security invariants (do not weaken).
Instructions file
Instructions for kirodotdev/KiroCrew: AGENTS.md is the single source of truth for this repository. Read it before any non-trivial change; it is imported below so it is always in context. This file intentionally holds no guidance of its own — do not add rules here, add them to AGENTS.md. The frontend has its own…
Skill Claude CodeCodex
On-call runbook and escalation procedures.
Skill Claude CodeCodex
Greeting patterns and onboarding tips.
Skill Claude CodeCodex
Browse sites that need a logged-in session with playwright-cli, using attach mode, saved storage state, or individual cookies. Use when a page is behind a login wall and a plain open lands on a sign-in screen.
Skill Claude CodeCodex
Conversational workflow for gathering user feedback and filing GitHub Issues on the KiroCrew repository. Load when the user clicks "Request a Feature", wants to report a bug, or suggest an improvement.
Skill Claude CodeCodex
Gracefully restart the KiroCrew gateway from within a running agent session, preserving conversation continuity via scheduled resume jobs. Use when user says "restart yourself", "restart gateway", "reload config", or after config changes that require a restart.
Skill Claude CodeCodex
Bootstrap a goal-driven self-improving AutoNudge loop. Give it a goal + anchor directory; it generates LOOP.md + GOAL.md + kanban board, then you write the Definition of Done and arm the loop. The running agent manages the board autonomously: finds issues, adds cards, resolves them, handoffs to Review, repeats until…
Skill Claude CodeCodex
Structured questioning to reach shared understanding before action. Walks the decision tree one branch at a time, checks memory for already-answered questions, saves every answer as a lesson. Use when user wants to think through a plan, align on approach, poke holes in a design, or figure out decisions before…
Skill Claude CodeCodex
Build, package, and publish KiroCrew external apps. Covers app.json manifest, UI components, crons, skills, self-healing install, git publishing, and common pitfalls.
Skill Claude CodeCodex
Complete CLI reference for KiroCrew commands. Use for help, commands, setup, how to, what can you do, getting started, onboarding.
Skill Claude CodeCodex
Convene a cross-vendor LLM council — the main session acts as Chairman and spawns several subagents, each pinned to a DIFFERENT model (Anthropic / OpenAI / DeepSeek / Zhipu / Qwen / etc. via kiro-cli). Three modes — synthesis (independent answers merged into one), vote (structured ballots + majority tally), and…
Skill Claude CodeCodex
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
Skill Claude CodeCodex
Build a reactive same-session autonomy loop using KiroCrew's AutoNudgeService. One long-lived dashboard session keeps working toward a goal — when its turn completes and no user input arrives within idlesecs, the service auto-injects a nudge message into the SAME session. Survives tab close, logout, and gateway…
Skill Claude CodeCodex
Check for and apply KiroCrew updates. Use when user says "update yourself", "check for updates", "are you up to date", "keep yourself updated", or "auto-update".
Skill Claude CodeCodex
Parallel discovery of performance hotspots (perf track) and failure surfaces (bug track) for the auto-improvement loop. Fans out one subagent per hot-path area or failure surface; each returns ONE concrete, behavior-preserving fix candidate (perf) or a reproducing test plus fix (bug). Discovery only — no code changes…
Skill Claude CodeCodex
Phase 1 of the auto-improvement loop — analyze the target repository, then design and calibrate the ruler (the trustworthy metric) BEFORE any optimization. Produces a low-variance primary metric, frozen anchors, a calibrated noise band, guardrails, reward-hack guards, and a mandatory canary that must clear the band or…
Skill Claude CodeCodex
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
Skill Claude CodeCodex
Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.
Skill Claude CodeCodex
Run a heuristic evaluation of a UI design (image, HTML, Figma, URL, or flow) the way an experienced designer would. Evaluates 4 categories (Visual & hierarchy, Usability & interaction, Accessibility, Content) using recognized frameworks, NN/g 0-4 severity, and evaluability-aware prioritization that never judges what…
Skill Claude CodeCodex
Interpret and act on batched visual edit requests produced by the Design Tweak app. Use when the user references a visual selection, a "design tweak" request, an edit request number, or asks you to apply pending visual edits.
Skill Claude CodeCodex
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
Skill Claude CodeCodex
ONLY for developing Kiro Crew itself -- if the project you are working on is anything else, ignore this skill: it drives Kiro Crew's own pod tooling, which does not exist in another repository. Runs end-to-end tests (backend API + frontend Playwright) for a Kiro Crew feature worktree against an ISOLATED throwaway pod…
Skill Claude CodeCodex
INTERNAL pet queue — generates the pet's 30-minute behavior schedule (moves, moods, notifications). NOT for user task or calendar planning.