plan-gate-executor
Enforce plan-first, approval-gated execution in repositories that use AGENTS or gate policies.
Skill by Emadgnia
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/emadgnia-plan-gate-executor-facfe0
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
plan-gate-executor- Description
- Enforce plan-first, approval-gated execution in repositories that use AGENTS or gate policies. Use when a task requires a dated plan file, explicit user approval before implementation, ordered gate execution, and evidence capture for validation, risks, rollback, and documentation sync.
- License
- MIT
- Instructions
- 59 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- openai.yaml · agents/
- gate-evidence-template.md · references/
- plan-checklist.md · references/
SKILL.md (first lines)
# Plan Gate Executor Use this skill to run delivery with strict gate discipline. ## Quick Workflow 1. Read the nearest `AGENTS.md` and identify mandatory gates, plan format, and approval requirements. 2. Scan core docs referenced by project policy (`README`, `Architecture.md`, `Skills.md`, `plans/README.md`, test guides). 3. Create a dated plan file in `plans/`. 4. Request explicit approval and stop implementation until approved. 5. Execute gates in order, recording evidence for each gate. 6. Summarize outcomes, residual risks, and next actions. ## Gate Execution Rules - Treat unclear requirements as blockers before coding. - Keep implementation scoped to the approved plan. - Require explicit user approval for protected operations (deploy/commit/branch switching or stricter project-specific rules). - Prefer deterministic evidence: - exact file paths changed - exact commands run - pass/fail results - rollback trigger and action ## Plan File Requirements Ensure every plan includes: - Goal and scope - Assumptions and missing inputs - Ordered execution steps - Validation steps and commands - Risks and mitigations - Rollback trigger and rollback verification - Explicit approval status Use [references/plan-checklist.md](references/plan-checklist.md) for a compact checklist. ## During Implementation - Keep a short execution log in the plan or a companion report file in `plans/`. - Update docs when behavior changes (`Skills.md`, `Architecture.md`, tests docs as applicable). - If a non-trivial decision changes architecture or flow, append a change-log entry to `Architecture.md`. ## Completion Criteria Consider the task complete only when all are true: - Approved plan exists and reflects actual work done. - Required validation commands ran or blockers are documented. - Risks and residual gaps are reported. - Documentation changes are synchronized with behavior changes. ## References - [references/plan-checklist.md](references/plan-checklist.md) - [references/gate-evidence-template.md](references/gate-evidence-template.md)
From Emadgnia/codex-agent-skills, MIT.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Feb 28, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Emadgnia/codex-agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from Emadgnia
- 0.414score
deployment-incident-responder
Emadgnia
Respond to deployment incidents by triaging failure signals, isolating root cause, executing safe rollback or forward-fix, and documenting incident outcomes.
SkillDFreshness: DClaude Code +9 - 0.414score
docs-governance-sync-enforcer
Emadgnia
Enforce synchronization across governance documentation after workflow or behavior changes.
SkillDFreshness: DClaude Code +9 - 0.414score
firebase-expo-monorepo-builder
Emadgnia
Build and stabilize Firebase plus Expo monorepos including workspace wiring, emulator setup, shared packages, and local run validation.
SkillDFreshness: DClaude Code +9 - 0.414score
git-pr-flow-governor
Emadgnia
Govern safe git and pull-request workflows with explicit ordering, risk-aware review priorities, and approval checks.
SkillDFreshness: DClaude Code +9 - 0.414score
obsidian-note-orchestrator
Emadgnia
Create and maintain Obsidian daily and weekly planning notes with carry-over tasks, consistent markdown sections, and stable wiki links.
SkillDFreshness: DClaude Code +9 - 0.414score
calendar-schedule-synthesizer
Emadgnia
Synthesize plans, meetings, and constraints into a coherent schedule with timezone-safe times and conflict resolution.
SkillDFreshness: DClaude Code +9
Cite this page
plan-gate-executor skill. Agent Mart. https://agentmart.dev/skills/emadgnia-plan-gate-executor-facfe0 (last updated 2026-10-24)