Execute Plan
- 59 installs
- 7.5k repo stars
- Updated August 5, 2026
- antinomyhq/forge
Execute-plan is a Forge/Claude skill that executes a structured task plan file to completion, tracking each task through pending, in-progress, done, and failed states.
About
Execute-plan runs structured task plans with automatic status tracking and progress updates. Given a plan file (plans/{date}-{task}-{version}.md), it reads pending tasks, marks each IN_PROGRESS, executes it, marks it DONE, and re-verifies completion at the end. A developer uses it to carry out a previously created plan step by step.
- Executes a structured plan file to completion with per-task status tracking
- Updates each task through PENDING, IN_PROGRESS, DONE, and FAILED states
- Re-reads the plan at the end to verify all tasks are completed
Execute Plan by the numbers
- 59 all-time installs (skills.sh)
- Ranked #1,559 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
execute-plan capabilities & compatibility
Free skill; pairs with a plan file produced by create-plan.
- Capabilities
- plan execution · task status tracking
- Use cases
- planning · project management
- Pricing
- Free
What execute-plan says it does
Execute structured task plans with status tracking.
Execute structured task plans with automatic status tracking and progress updates.
npx skills add https://github.com/antinomyhq/forge --skill execute-planAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 59 |
|---|---|
| repo stars | ★ 7.5k |
| Last updated | August 5, 2026 |
| Repository | antinomyhq/forge ↗ |
What it does
Execute a structured plan file to completion, updating each task's status from pending to done and verifying at the end.
Who is it for?
Developers running a previously written plan file step by step with automatic status tracking.
Skip if: Ad-hoc work with no plan file; it expects a plans/{date}-{task}-{version}.md input.
When should I use this skill?
The user provides a plan file path like plans/{current-date}-{task-name}-{version}.md or explicitly asks to execute a plan file.
What you get
Every task in the plan executed and marked DONE, with a final re-read verifying completion.
- Plan file with all tasks marked DONE
- Progress updates per task
By the numbers
- 4 task-status markers: PENDING, IN_PROGRESS, DONE, FAILED
- 6-step execution loop from commitment to final verification
Files
Execute Plan
Execute structured task plans with automatic status tracking and progress updates.
Commitment to Completion
When a plan is provided, all tasks in the plan must be completed. Before starting execution, recite:
"I will execute this plan to completion. All the 20 tasks will be addressed and marked as DONE."
Execution Steps
STEP 1: Recite the commitment to complete all tasks in the plan.
STEP 2: Read the entire plan file to identify pending tasks based on task_status.
STEP 3: Announce the next pending task and update its status to IN_PROGRESS in the plan file.
STEP 4: Execute all actions required to complete the task and mark the task status to DONE in the plan file.
STEP 5: Repeat from Step 3 until all tasks are marked as DONE.
STEP 6: Re-read the plan file to verify all tasks are completed before announcing completion.
Task Status Format
Use these status indicators in the plan file:
[ ]: PENDING
[~]: IN_PROGRESS
[x]: DONE
[!]: FAILEDExample Usage
1. User provides: "Execute plan at plans/2025-11-23-refactor-auth-v1.md" 2. Recite commitment: "I will execute this plan to completion..." 3. Read the plan file 4. Find first [ ] (PENDING) task 5. Update to [~] (IN_PROGRESS) 6. Execute the task 7. Update to [x] (DONE) 8. Move to next PENDING task 9. Repeat until all tasks appear DONE 10. Re-read plan file to verify completion 11. Announce completion
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493kFAQ
What status markers does it use?
[ ] PENDING, [~] IN_PROGRESS, [x] DONE, and [!] FAILED, updated in the plan file as it works.
How does it confirm completion?
After marking all tasks DONE, it re-reads the plan file to verify all tasks are completed before announcing completion.