Menu
Use for every coding or script execution task. Applies to code edits and code reviews as well as tests builds validation debugging shell commands automation and blocked execution reports. Ensures exceptions are surfaced instead of muted.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when changing what a running devloop harness serves — pointing it at a different directory or worktree, or making the live harness serve newer or different code (a newer commit, another branch, or in-progress edits) without a wasteful restart.
Use when verifying that a UI change works end to end by driving the running app in a real browser — confirming a fix, reproducing a reported UI symptom, or proving a wizard/form/flow behaves — with Playwright against the exact code under review.
Enforce a Roborev plus Kata development workflow for code changes. Use when Codex is asked to implement, fix, refactor, or review work tracked by Kata and Roborev, especially when branch discipline, non-blocking review jobs, validation gates, SemVer, changelog checks, and final delivery reporting matter.
Use when working on GitHub pull requests that need PR-ready validation, review-thread replies, reviewer mentions, linked external references, or merge readiness checks.
Create or review a standalone repository that publishes a set of Codex or Claude skills with shared validation, linking, eval, and agent metadata conventions.
Prepare small, reviewable local commits with explicit rationale, SemVer impact, task hygiene, branch cleanup expectations, and clear commit commentary. Use when asked to commit work, prepare a PR-ready change, decide version impact, write commit messages, or clean up merged feature branches.
| name | coding |
| description | Use for every coding or script execution task. Applies to code edits and code reviews as well as tests builds validation debugging shell commands automation and blocked execution reports. Ensures exceptions are surfaced instead of muted. |
If code execution is blocked by an exception, surface the exception. Do not mute exceptions.
Treat blocked code or script execution as a failed or incomplete validation run. Do not report validation as passed after an exception.
Do not replace a command with a guard branch that skips execution. Run the command and let missing configuration, subprocess errors, and runtime exceptions fail visibly.
Changing a guard branch from success to non-zero failure is still wrong when it skips the command that should have produced the exception.
Do not inline a script written in one programming language inside a script written in another programming language. Keep each language in its own file and invoke that file from the wrapper script.
Do not compose static multiline strings through consecutive function calls such as repeated append, write, add, or concatenation calls. When writing or reviewing code, reject that shape and use the language's idiomatic multiline string form, such as a heredoc, raw string literal, template literal, or triple-quoted string.
When modifying existing code that builds a static multiline string with repeated calls, rewrite the whole static value as one multiline string. Do not preserve or extend the repeated-call sequence.
Do not add machine-specific filesystem paths to scripts, code, configuration, or documentation unless the user explicitly asks for that exact path. Prefer repo-relative paths, source-relative paths, or environment variables. If an example is meant to run from the repository root, document the command directly from that root; do not prepend placeholder absolute paths such as /path/to/project.
Source notes live in references/notes.md.
