Instructions file CodexOpenCode
Instructions for PanPanFR/oh-my-kilo: Global rules live in rules/.md (loaded via instructions in kilo.jsonc) - single source of truth. This file only indexes them; do not duplicate their content here.
Agent
Read-only Q&A - explain code, explore concepts, investigate without changing anything.
Agent
Default agent - implementation, debugging, general development, delegates to subagents.
Agent
Systematic troubleshooting, root cause analysis, diagnostics.
Agent
Technical writing specialist - creates and improves documentation.
Agent
Fast codebase exploration - scouting, pattern finding, file location.
Agent
Multi-step implementation executor - UI/frontend builds, refactors, and well-defined delegated tasks.
Agent
System design, architecture planning, implementation plans. Callable as primary agent or subagent.
Agent
External research specialist - library/framework/API documentation lookups with cited findings.
Agent
Code and security review specialist - reviews diffs against repo standards, spec, and a security baseline; read-only.
Agent
Test specialist - writes and runs test suites, iterates failures in isolation.
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts 65% of output tokens while keeping full technical accuracy by speaking like a caveman. Use when user wants terse, token-efficient replies or asks for 'caveman mode'.
Skill Claude CodeCodex
This skill embodies the principles of "Clean Code" by Robert C. Martin (Uncle Bob). Use it to transform "code that works" into "code that is clean." Trigger with "clean code", "code review", "review code quality", "refactor for readability", "naming conventions", "function size", or when reviewing code for quality…
Skill Claude CodeCodex
Unified Cloudflare platform skill: Workers, Durable Objects, Wrangler CLI, KV, D1, R2, AI, Vectorize, Queues, Workflows, Containers, Pipelines, Secrets Store, Agents SDK, Pages, security (WAF, DDoS, Turnstile), networking (Tunnel, Spectrum), IaC (Terraform, Pulumi). Use for any CF task. Retrieval-first.
Skill Claude CodeCodex
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…
Skill Claude CodeCodex
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
Skill Claude CodeCodex
Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", "API docs", "architecture doc", or when the user needs help with any form of technical writing. Also use when writing README, CHANGELOG, or any markdown documentation.…
Skill Claude CodeCodex
Use when you have a written implementation plan to execute in a separate session with review checkpoints.
Skill Claude CodeCodex
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive…
Skill Claude CodeCodex
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
Skill Claude CodeCodex
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Skill Claude CodeCodex
Compact the current conversation into a handoff document for another agent to pick up.
Skill Claude CodeCodex
Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find…
Skill Claude CodeCodex
Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this…