AI Agent Workflow Collection

Run recurring Codex automations with Ceratops defaults. Use when an automation run needs shared policy for re-opening prompt and helper contracts, keeping task-specific logic in the automation prompt or helper scripts, suppressing routine clean-run alerts, avoiding routine automation memory, and reporting no-alert or no-memory conflicts explicitly.

Audit a repository after large refactors, branch merges, or parallel agent threads for contradictions between implementation, docs, configs, tests, examples, and control files. Use when the goal is post-merge validation, release-readiness consistency checking, documentation-drift detection, or merged-only edge-case hunting rather than style review.

Stage committed Ceratops skill changes into the runtime checkout's local release/ branch for coherent local preview. Use when Codex should merge ready task-worktree branches into a release branch created from main, switch the runtime checkout to that branch, update the local skill install, and run the local validation batch before GitHub shipping.

Review the Ceratops org, repo, code, PR readiness, and artifact health contracts against current GitHub, repo-content, and registry standards, then report proposed contract or checker updates for explicit approval.

Analyze recent Codex runs for avoidable credit spend, including deterministic rework, and recommend small prompt, rule, skill, helper, workflow, or validation controls.

Break repeated failed fix loops by requiring full failure analysis before more code changes when repeated fixes have not solved the same symptom.

Ship Ceratops or other local Codex skill changes from the runtime checkout's staged release/ branch through GitHub and back to the installed runtime on main. Use when Codex should validate staged skill changes, confirm the runtime checkout is on the intended release branch, publish the batch through GitHub, then restore the runtime checkout and installed skills to synced main.

Merge a GitHub pull request safely with Ceratops defaults, starting with a live scripted readiness check and ending with verified cleanup.

Create, fork, or production-harden a local software project as a public GitHub repository and publish the correct public artifact registry output with Ceratops defaults, using live scripted GitHub checks before closing.

Process Dependabot, Renovate, security, and manual dependency maintenance work through GitHub with Ceratops defaults, using scripted live repo and PR checks before merge decisions.

Audit and repair GitHub repository health with Ceratops defaults, using scripted live checks first for machine-checkable GitHub settings.

Route Ceratops GitHub repository lifecycle work to action references for create-or-publish, contracts-review, health-audit, dependency-maintenance, ship-change, and merge-pr work. Use when Codex should create or harden a repo, review GitHub/code/repo/org/PR/artifact contracts, audit or repair repo health, process dependency PRs or alerts, ship local changes through GitHub, or finalize a ready PR.

Ship local repository changes through GitHub and any relevant artifact registry with Ceratops defaults, using scripted live repo and PR checks before merge decisions.

Route Ceratops governance work across prompt optimization, advisory skill optimization, regression-safe instruction updates, and cross-scope governance consistency audits. Use when Codex should rewrite a rough prompt without executing it, recommend exact changes to existing skills without applying them, diagnose and route approved instruction changes, or audit alignment across AGENTS files, automations, directly referenced helpers, and governance owners.

Produce a durable rule or instruction update from a concrete failure, gap, weak draft, or current workflow miss while preserving the original rule intent.

Transform raw, simple, vague, or under-specified prompts into clearer structured prompts without changing intent or answering the prompt.

Propose focused rule-update recommendations after a concrete agent failure or miss caused or allowed by existing or missing instructions. Use when the user invokes $Ceratops-Propose-Rules-Update or $ceratops-propose-rules-update to diagnose instruction causes and propose exact updates to AGENTS.md rules, SKILL.md rules, automation prompts, helper contracts, policy lines, or prompt rules.

Route Ceratops repository lifecycle work to action references for repository creation, compatibility, contracts, health, dependencies, local promotion, deterministic deployment, GitHub shipping, and PR merge. Use when Codex should create or harden a repository, make it Ceratops-compatible, review its contracts, disposition CodeQL, maintain dependencies, promote selected task branches into a local release branch with or without deployment, ship a staged branch through guarded GitHub merge and post-merge deployment, or finalize an already-ready PR.

Analyze recent Codex runs for deterministic rework causes that could be prevented or reduced by better prompts, rules, skills, helpers, or validation gates.

Optimize a provided rule or instruction after a failure, gap, or weaker first attempt. Use when the user explicitly invokes $Ceratops-Rule-Optimizer or $ceratops-rule-optimizer to refine rule text, instruction text, policy lines, prompt rules, AGENTS.md rules, SKILL.md instructions, or automation guidance.

Create a brand-new Ceratops skill in codex-skills, integrate it into the shared section system and repo metadata, validate the result with the needed checks, and make it available locally through the runtime release/ branch by default. Use when the user asks for a new Ceratops skill rather than an update to an existing one.

Apply a simple Ceratops skill change directly on an active release branch, commit it there, and update only the affected runtime skill copy.

Route Ceratops or compatible skill lifecycle work to action references for create, update, skills-consistency-and-contract-review, fast-change, change-promotion, and ship-to-remote work. Use when Codex should create a skill, update skill source or shared governance surfaces, audit skill consistency, maintain skill-design contracts, apply an explicit fast release-branch change, promote committed skill changes into a local release/runtime preview, or ship a staged skills batch through GitHub.

Optimize existing Codex or Ceratops skills by proposing targeted updates to structure, triggers, workflow, constraints, output contracts, or done criteria.