Instructions file CodexOpenCode
AGENTS.md instructions for Hawkynt/ClaudeCodePortable, covering agent guide — claudecodeportable, what this is, commits, the loop (always, in this order) and code conventions.
Skill Claude CodeCodex
Use after completing any substantive piece of work (code change, analysis, document, configuration, answer to a hard question) and BEFORE presenting it as done. Switches you from author to attacker - you try to refute your own work and only present it if it survives. Do not skip because the work "looks clean"…
Skill Claude CodeCodex
Use when starting work in a LARGE or UNFAMILIAR codebase, when a repo already contains an INDEX.md, or when repeatedly grepping for where something is defined. Generates and consults INDEX.md - a symbol locator (namespaces, types, enums, constructors, functions, methods with parameters, globals/statics, one-line…
Skill Claude CodeCodex
Use immediately before declaring any task complete, closing any request, or presenting work as finished. Forces a completion audit against the ORIGINAL request - every explicit requirement ticked off as done-and-verified, everything skipped named plainly. Do NOT confuse it with correctness review (that is…
Skill Claude CodeCodex
Use at the start of any task and whenever choosing how many probes, searches, or tool calls to spend - answering a question, investigating code, researching, debugging. Matches depth to task size: trivial asks get trivial effort, deep tasks get a plan and sustained effort, independent lookups run in parallel. Do NOT…
Skill Claude CodeCodex
Use during any multi-step task when you feel the pull to stop and ask "should I continue?", "want me to also do X?", or to hand back partial work. Forces completion of what was asked - ambiguities get a stated assumption and forward motion, not a stall. Do NOT use it to bulldoze past genuine forks the user must own…
Skill Claude CodeCodex
Fetch a webpage as clean, structured Markdown via the jina.ai reader (r.jina.ai) instead of raw HTML — use whenever you need to read web content and want to save tokens, or when a normal fetch is blocked (HTTP 403/401), returns messy/boilerplate HTML, or the page is JavaScript-rendered (SPA, docs sites, wikis like…
Skill Claude CodeCodex
Use whenever you are about to assert or act on a fact about a system - what a function does, what a config is set to, what is deployed, what a table contains, what a dependency's version is. Forces verification against the LIVE system before the assertion. Docs, comments, READMEs, and your own memory are treated as…
Skill Claude CodeCodex
Use when writing to or reading from any persistent memory an agent keeps across sessions - CLAUDE.md, memory files, notes, project docs meant for future sessions. Governs WHAT deserves persisting, HOW to write it so it survives time, and the recall rule: verify remembered facts against live state before acting on…
Skill Claude CodeCodex
Use before starting ANY task that involves more than one edit, file, or step - coding, refactoring, writing, configuration, migrations. Forces a short written plan (goal, unknowns, success criteria, step order) BEFORE the first change. Do not use for single-line fixes or pure questions.
Skill Claude CodeCodex
Use when composing conversational answers, explanations, documentation, reports, or summaries - the places where formatting tends to metastasize. Enforces the minimum-formatting rule - prose by default, bullets/headers/bold only when the content genuinely demands them - plus the one-question rule and the no-padding…
Skill Claude CodeCodex
Use whenever something is broken and you are about to fix it - a failing test, a bug report, a crash, wrong output, flaky behavior. Forces reproduce -> isolate -> fix the cause -> re-run the repro, and bans fixes without a failing observation. Do NOT use for building new features or for changes where nothing is broken…
Skill Claude CodeCodex
Use whenever you produce prose a human will read - documentation, READMEs, reports, summaries, commit messages, emails, blog drafts, PR descriptions. Runs a cutting pass where every sentence must earn its place. Target: 30 percent shorter with zero information loss. Do not use on code or on text the user asked you to…
Skill Claude CodeCodex
Use on every task where you will modify existing work - code, documents, configs. Fences your changes to exactly what was asked. Adjacent problems get FLAGGED, never silently fixed. Keeps diffs minimal and reviewable. Do not use it to refuse legitimate follow-through the task actually requires.
Skill Claude CodeCodex
Use whenever deciding whether to search the WEB and how to construct the queries - answering factual questions, evaluating products/versions/APIs, encountering unfamiliar names or terms. Encodes the rate-of-change rule, the unrecognized-entity rule, effort scaling, query construction, and source-trust calibration. Do…
Skill Claude CodeCodex
Use whenever persistent agent memory is read, written, or has grown past its budget - the first time memory is consulted in a session, whenever something worth remembering appears, and whenever MEMORY.md or a topic file exceeds its size budget. Implements a two-tier structure (slim MEMORY.md index linking memory-.md…