Executing Plans — Single-Session Fallback
> **Type:** Rigid process
Best use case
Executing Plans — Single-Session Fallback is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
> **Type:** Rigid process
Teams using Executing Plans — Single-Session Fallback should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/executing-plans/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Executing Plans — Single-Session Fallback Compares
| Feature / Agent | Executing Plans — Single-Session Fallback | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
> **Type:** Rigid process
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Executing Plans — Single-Session Fallback > **Type:** Rigid process > **Trigger:** Have plan to execute but NO subagent support available > **Fallback for:** subagent-driven-development ## Iron Law ``` FOLLOW THE PLAN EXACTLY — DEVIATIONS REQUIRE EXPLICIT APPROVAL ``` ## Purpose Simpler version of subagent-driven-development for environments without subagent capabilities. Loads the plan, reviews it critically, then executes tasks sequentially in the current session. ## Process ### Phase 1: Load and Review 1. Read the full implementation plan 2. Review critically — raise concerns BEFORE starting 3. Identify potential issues, missing context, unclear steps 4. Get user approval to proceed (or modify plan first) ### Phase 2: Execute Tasks For each task in order: 1. Mark task as `in_progress` 2. Follow steps exactly as written in the plan 3. Run tests after each step (verify red → green) 4. Mark task as `completed` when all steps pass 5. If stuck → mark as `blocked`, explain why, ask for guidance ### Phase 3: Finish 1. Run full test suite 2. Review all changes holistically 3. Invoke `finishing-a-development-branch` skill ## Key Differences from Subagent Version | Aspect | Subagent-Driven | Executing-Plans | |--------|-----------------|-----------------| | Context | Fresh per task | Accumulated (risk of pollution) | | Review | Two-stage (spec + code) | Self-review only | | Parallelism | Yes (multiple agents) | No (sequential) | | Quality | Higher (isolation) | Lower (fatigue, bias) | ## Mitigation Strategies Since you lack fresh context per task: - **Re-read the plan** before each task (reset mental model) - **Self-review checklist** after each task (spec compliance + quality) - **Request human review** at task boundaries for complex features - **Commit frequently** — each task gets its own commit ## Rationalization Table | Excuse | Reality | |--------|---------| | "I'll adjust the plan as I go" | Deviations need approval. Document, ask, then adjust. | | "This step is wrong, I'll fix it" | Maybe the step is right and you're wrong. Verify first. | | "I can combine these tasks" | Plan tasks are independent for a reason. Execute separately. | | "Tests aren't needed for this step" | TDD is non-negotiable. Write the test. |
Related Skills
Writing Plans — TDD-Sized Task Breakdown
> **Type:** Rigid process (follow structure exactly)
Singleton Patterns
> Manage module-level state safely in serverless and edge environments using globalThis attachment, initialization guards, and connection pooling.
YAML Prompt Library
> Store reusable AI prompts as YAML files with structured messages, variables, and test data for version-controlled prompt engineering.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
wireframing
Wireframing patterns including layout grids, content blocks, responsive breakpoints, and page layout patterns for landing pages, dashboards, and forms. Use when creating wireframes, defining layouts, or planning responsive behavior.
windows-registry-editor
Expert Windows Registry editor and optimizer via PowerShell. Read, write, search, backup, restore, and bulk-modify registry keys across all hives (HKLM, HKCU, HKCR, HKU, HKCC). Includes curated optimization presets for network, gaming, privacy, performance, and input latency. Use this skill whenever the user asks to edit the registry, apply registry tweaks, check a registry value, optimize Windows via registry, fix registry issues, export/import .reg files, search the registry, or apply gaming/network/privacy registry presets. Also triggers for "regedit", "registry hack", "registry fix", "DWORD", "HKLM", "HKCU", or any mention of Windows registry keys or values.
windows-network-optimizer
Diagnose, optimize, and verify Windows 11 network and system performance via PowerShell. Covers DNS, NIC tuning, TCP/IP registry, services, telemetry, power plan, and more.
windows-error-debugger
Diagnose, debug, and fix Windows crashes, BSODs, driver failures, and system errors via PowerShell. Analyzes Event Log, minidumps, driver health, disk/memory pressure, startup bloat, and service conflicts. Builds a growing knowledge base of resolved issues per machine. Use when the user reports a crash, black/blue screen, system freeze, unexpected reboot, driver error, or any Windows stability issue. Also triggers for "BSOD", "blue screen", "black screen", "crash", "system error", "bugcheck", "minidump", "driver failure", "unexpected shutdown", "paging file too small", "system hang", "Windows froze", "PC crashed", "kernel error", or any mention of Windows Event Log errors.
White-Label Config
> Transform any application into a customizable, self-hostable product with typed configuration, feature flags, and runtime env overrides.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Vitest Unit Patterns
> Design fast, isolated unit tests that validate business logic without network, database, or browser dependencies using Vitest.