codex-reasoning

---

LIBRARY-FIRST PROTOCOL (MANDATORY)

Before writing ANY code, you MUST check:

Step 1: Library Catalog

• Location: .claude/library/catalog.json
• If match >70%: REUSE or ADAPT

Step 2: Patterns Guide

• Location: .claude/docs/inventories/LIBRARY-PATTERNS-GUIDE.md
• If pattern exists: FOLLOW documented approach

Step 3: Existing Projects

• Location: D:\Projects\*
• If found: EXTRACT and adapt

Decision Matrix

Match	Action
Library >90%	REUSE directly
Library 70-90%	ADAPT minimally
Pattern exists	FOLLOW pattern
In project	EXTRACT
No match	BUILD (add to library after)

---

Purpose

Coordinate Codex through reasoning checkpoints, tests, and evidence gathering when autonomy must stay bounded.

Trigger Conditions

• Use this skill when: Need Codex to reason through multi-step fixes or analyses with reviewable checkpoints.
• Reroute when: If fully unattended work is acceptable, use codex-auto.

Guardrails (Inherited from Skill-Forge + Prompt-Architect)

• Structure-first: every platform skill keeps SKILL.md, examples/, and tests/ populated; create resources/ and references/ as needed. Log any missing artifact and fill a placeholder before proceeding.
• Confidence ceilings are mandatory in outputs: inference/report 0.70, research 0.85, observation/definition 0.95. State as Confidence: X.XX (ceiling: TYPE Y.YY).
• English-only user-facing text; keep VCL markers internal. Do not leak internal notation.
• Adversarial validation is required before sign-off: boundary, failure, and COV checks with notes.
• MCP tagging for runs: WHO=codex-reasoning-{session}, WHY=skill-execution, namespace skills/platforms/codex-reasoning/{project}.

Execution Framework

1. Intent & Constraints — clarify task goal, inputs, success criteria, and risk limits; extract hard/soft/inferred constraints explicitly.
2. Plan & Docs — outline steps, needed examples/tests, and data contracts; confirm platform-specific policies.
3. Build & Optimize — apply platform playbook below; keep iterative checkpoints and diffs.
4. Validate — run adversarial tests, measure KPIs, and record evidence with ceilings.
5. Deliver & Hand off — summarize decisions, artifacts, and next actions; capture learnings for reuse.

Platform Playbook

• Workflow patterns:
  • Plan-execute-review loops with explicit hypotheses
  • Attach tests/benchmarks at each checkpoint
  • Summarize diffs with evidence and open risks
• Anti-patterns to avoid: Skipping checkpoint notes and evidence, Letting Codex run without bounding commands, Shipping without regression tests
• Example executions:
  • Guide Codex through debugging flaky integration tests
  • Run reasoning loop to redesign API boundaries with proposals

Documentation & Artifacts

• SKILL.md (this file) is canonical; keep quick-reference notes in README.md if present.
• examples/ should hold runnable or narrative examples; tests/ should include validation steps or checklists.
• resources/ stores helper scripts/templates; references/ stores background links or research.
• Update metadata.json version if behavior meaningfully changes.

Verification Checklist

• Trigger matched and reroute considered
• Examples/tests present or stubbed with TODOs
• Constraints captured and confidence ceiling stated
• Validation evidence captured (boundary, failure, COV)
• MCP tags applied for this run

Confidence: 0.70 (ceiling: inference 0.70) - Standardized platform skill rewrite aligned with skill-forge + prompt-architect guardrails.