Agent skill

codex-prompting-local

Portable Codex prompt, review-contract, and resume-handoff guidance adapted from codex-plugin-cc for this repo's Nix-managed Codex CLI and Claude Code setup. Use when: - Composing prompts for Codex or GPT-5.4-based subagents - Designing structured review or adversarial-review prompt contracts - Writing resumable task prompts or result handoffs - Re-expressing useful old slash-command workflows on the skills side instead of reviving slash commands

Stars 9
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/i9wa4/dotfiles/tree/main/nix/home-manager/agents/skills/codex-prompting-local

SKILL.md

codex-prompting-local

This skill adapts the portable parts of codex-plugin-cc to the current nix/home-manager/agents/ architecture.

Use it for prompt and output contracts, not as a new runtime control plane. This repo's runtime authority still lives in Nix-managed hooks, agents, MCP definitions, and generated home files.

Core rules:

  • Use one concrete task per Codex run unless there is a clear reason to batch.
  • Prefer compact XML-style prompt blocks over long freeform instructions.
  • Tell Codex what done looks like, how to verify it, and when to keep going by default.
  • Use machine-readable review output only when the downstream consumer benefits from it. Otherwise keep the repo's normal findings-first prose review style.
  • Keep resumable results thread-aware and action-oriented. If a thread ID is known, surface it explicitly. If not, do not invent one.
  • Treat old slash-command behavior as workflow intent to preserve in skills, scripts, or prompts. Do not reintroduce plugin frontmatter, AskUserQuestion, or .claude-plugin assumptions.

Recommended workflow:

  1. Pick the smallest prompt shape that fits the task.
  2. Add only the blocks the task actually needs.
  3. Add a structured review contract only for review surfaces that should emit parseable output.
  4. For long-running or multi-turn work, write the result so it can be resumed cleanly from saved handoff context.

Open these references as needed:

  • references/prompt-blocks.md
  • references/review-output-contract.md
  • references/resume-handoff.md

Expand your agent's capabilities with these related and highly-rated skills.

i9wa4/dotfiles

subagent-review

Argument-driven code/design review wrapper. Invokes reviewer sub-skills for each specified engine+tier label. Defaults to 'cc cx' (10 reviewers) if no arguments given. Argument format: space-separated labels from {cc, cc-deep, cx, cx-deep} Examples: 'cc cx' (default), 'cc-deep cx-deep', 'cc', 'cx-deep' Use when: - Running code reviews on PRs, commits, or branches - Running design reviews on issues or documents - Need multi-perspective review (security, architecture, code, QA, historian)

9 0
Explore
i9wa4/dotfiles

brainstorming

Ambiguity-reduction workflow for requests that are not yet plan-ready or implementation-ready. Use when there are multiple plausible approaches, the task is user-facing or design-shaping, requirements are fuzzy, or Codex needs to compare 2-3 options with trade-offs before choosing a direction.

9 0
Explore
i9wa4/dotfiles

databricks-local

Databricks local additions - Queries API, VARIANT/JSON, Dashboard API, dbt integration, Jupyter kernel Supplements the official `databricks` skill with project-specific patterns. Use when: - Working with Databricks Queries API (saved queries) - Handling VARIANT type or JSON operations - Working with Lakeview Dashboard API - Integrating dbt with Databricks JSON/VARIANT columns - Running Jupyter notebooks with Databricks kernel

9 0
Explore
i9wa4/dotfiles

nix

Nix commands and package management guide. Use when: - Using nurl for hash acquisition

9 0
Explore
i9wa4/dotfiles

bigquery-local

BigQuery local additions - cost-aware query patterns and project conventions. Supplements general BigQuery knowledge with guardrails. Use when: - Running bq commands - Writing GoogleSQL queries - Designing partitioned/clustered tables

9 0
Explore
i9wa4/dotfiles

tmux

tmux pane operations guide for debugging and monitoring separate panes Use when: - Sending commands to another tmux pane - Capturing output from another tmux pane - Monitoring long-running commands in separate panes - Debugging devcontainer build/up operations - Working with multiple panes in parallel

9 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results