.claude/skills/codex-document-flow/SKILL.md
Document-centered workflow for design, planning, reverse-engineering, and updates using Codex skills only. Replaces document-focused subagent chains.
npx skillsauth add ssaattww/excelreport codex-document-flowInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill follows the non-entry execution contract standard.
Required contract_extensions: mode, target_docs.
See codex-execution-contract.md and non-entry-execution-contract-template.md for full rules.
input:
objective: "Update design and plan docs for feature X"
contract_extensions: { mode: "update", target_docs: ["docs/design/feature-x-design.md", "docs/plans/feature-x-plan.md"] }
output:
status: "completed"
quality_gate:
gate_id: "document-alignment-check"
gate_type: "document"
trigger: "post-document review"
criteria:
- "Target documents are updated"
- "Document set is internally consistent"
result: "pass"
evidence:
- "Target docs aligned"
blockers: []
branching:
on_pass: "handoff"
on_fail: "revise"
max_cycles: 2
contract_extensions: { mode: "update", target_docs: ["docs/design/feature-x-design.md", "docs/plans/feature-x-plan.md"] }
codex-execution-contract.md.status, summary, changed_files, tests, quality_gate, blockers, next_actions.../workflow-entry/references/non-entry-execution-contract-template.md (objective, scope, constraints, acceptance_criteria, allowed_commands, sandbox_mode) before proceeding.contract_extensions: mode, target_docs.non-entry-execution-contract-template.md.create: new document generation.update: modify existing documents while preserving rationale and change history.reverse: generate documents from current codebase behavior.documentation-criteria templates.[Stop: pre-design-approval] + [Approve: design-approval] before moving to the next phase.| Scale | Required docs | |---|---| | Small | simplified plan, optional design note | | Medium | Design Doc + Work Plan | | Large | PRD + Design Doc + Work Plan, ADR when needed |
[Stop: pre-design-approval] + [Approve: design-approval].quality_gate emission and branching using quality-gate-evidence-template.md.gate_id, gate_type, trigger, criteria, result, evidence, blockers, branching.gate_type: document for document quality and completeness checks.result: pass|fail|blocked before handoff.result: blocked, emit [Stop: quality-gate-failed] and pause for escalation handling.Use canonical markers: [Stop: <Gate Name>].
Classify every stop as approval_gate or escalation_gate.
At each stop, emit a full gate record: gate_name, gate_type, trigger, ask_method, required_user_action, resume_if, fallback_if_rejected.
Default ask_method is AskUserQuestion.
Resume an approval_gate only with explicit user approved: true; resume an escalation_gate only after user direction or reroute.
Respect batch boundary: document phases stay human-gated, and transitions into implementation require [Stop: pre-implementation-approval].
Enforce max_revision_cycles: 2; overflow requires human intervention.
Agent-local document review approvals never replace user approvals.
Stop points for this skill:
[Stop: pre-design-approval] (approval_gate)[Stop: pre-implementation-approval] (approval_gate)[Stop: high-risk-change] (approval_gate)[Stop: requirement-change-detected] (escalation_gate)[Stop: quality-gate-failed] (escalation_gate)[Stop: revision-limit-reached] (escalation_gate)Full protocol and payload schema: ../workflow-entry/references/stop-approval-section-template.md.
databases
Unified deterministic entry for workflow requests. Centralizes routing with stop/approval and sandbox controls.
development
Sends commands to another tmux pane. Use when requests include phrases like "run it in another pane," "send via tmux," or "ask Claude Code to execute."
tools
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
development
Single-agent execution loop for implementation tasks. Replaces task-executor/quality-fixer subagent cycle with direct Codex skill-driven implementation and quality gates.