codex-task-waves

Use when the user says "have codex fix this" / "have codex implement this" / "let codex handle this" / "give this to codex" / "delegate this to codex" for a single task with context already in scope (a Jira ticket, GitHub issue, file diff, bug, or described change). Plans the work, splits it into reviewable waves, dispatches codex per wave with review and correction between waves before opening a PR. Not for multi-issue parallel batches (use codex-issue-waves) or one-shot codex runs without planning (use invoking-codex-exec).

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tightly orchestrated, highly actionable multi-wave workflow with strong validation feedback loops and clear sequencing. Its main weakness is mild verbosity around repeated orchestration-boundary enforcement that could be consolidated.

Suggestions

Consolidate the repeated 'claude never edits/reviews' rule into one canonical statement; the Red flags table re-explains it across several rows, which adds tokens without new information.

Move the per-wave reviewer checklist and the corrector/escalation recipes into a referenced file (e.g. references/wave-review-checklist.md) to reduce inlined detail and improve progressive disclosure.

Tighten the 'Why codex for review' section — the consistency/efficiency/separation rationale can be one line since the boundary rule is already stated earlier.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but the Red flags table and several verbose explanations of 'why codex for review' restate the same orchestration-boundary point multiple times, adding padding that could be tightened.	3 / 5
Actionability	Highly executable: concrete git commands (git status --short, git log --oneline, git diff <last-wave-commit>..HEAD), a runnable python3 JSON-validation one-liner, exact prompt fragments to embed, and specific per-wave step sequences.	5 / 5
Workflow Clarity	Clear phased sequence (Identify → Plan → Split → Per-wave loop → Finalize) with explicit validation checkpoints (status verification, reviewer verdict gates, full project verification between waves, malformed-JSON recovery, 3-cycle escalation).	5 / 5
Progressive Disclosure	Well-organized with clearly signaled one-level references to required sub-skills (invoking-codex-exec, superpowers:writing-plans, superpowers:using-git-worktrees) and sectioned structure; no bundle files exist so some detail that could live in a reference is inlined, a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

91%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: concrete actions, natural trigger phrases, explicit what/when guidance, and clear disambiguation from sibling skills. It is slightly long but the verbosity serves distinctiveness rather than padding.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Plans the work, splits it into reviewable waves, dispatches codex per wave with review and correction between waves before opening a PR' — with minor gaps in surface coverage of all sub-actions.	4 / 5
Completeness	Explicitly answers both 'what' (plans, splits into waves, dispatches codex, opens PR) and 'when' via concrete trigger phrases plus explicit exclusion guidance for adjacent skills.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural trigger phrases a user would say ('have codex fix this', 'have codex implement this', 'let codex handle this', 'give this to codex', 'delegate this to codex') plus synonym variations.	5 / 5
Distinctiveness Conflict Risk	Clear niche (single-task codex delegation with planning and waves) with explicit disambiguation against codex-issue-waves and invoking-codex-exec, minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ddnetters/homelab-agent-skills
Path: codex-task-waves/SKILL.md
Commit: 808c382

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.