Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
buiducnhat avatar

Execute Plan

  • 487 installs
  • 52 repo stars
  • Updated July 6, 2026
  • buiducnhat/agent-skills

execute-plan is a Claude agent skill that runs approved ExecPlans phase-by-phase with verification gates and deviation logs for developers who need tracked implementation execution with a final report.

About

execute-plan is a buiducnhat agent-skills workflow for running an already-approved ExecPlan or implementation checklist in batch or interactive mode. Each phase records implemented work, verification commands, and notes, then aggregates results into an execution report with a verification matrix covering lint, type check, tests, build, and manual QA status. The skill logs approved deviations, blockers with resolutions, and follow-up tasks when work completes with caveats. Developers reach for execute-plan after planning is signed off and they want disciplined, gate-checked delivery instead of ad-hoc task jumping. Output follows a structured Execution Report template with per-phase pass or warning markers.

  • Strict scope adherence to pre-approved ExecPlan-style documents with living progress notes
  • Batch or interactive execution modes with per-phase ✅/⚠️ status
  • Verification matrix: lint, typecheck, tests, build, and manual QA commands
  • Deviation, blocker, and follow-up sections with changed-files inventory
  • Argument hint accepts plan paths such as docs/.plans/YYMMDD-HHmm-<slug>/SUMMARY.md

Execute Plan by the numbers

  • 487 all-time installs (skills.sh)
  • Ranked #768 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/buiducnhat/agent-skills --skill execute-plan

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs487
repo stars52
Security audit3 / 3 scanners passed
Last updatedJuly 6, 2026
Repositorybuiducnhat/agent-skills

How do you execute an approved plan with verification?

Run an already-approved ExecPlan or implementation checklist phase-by-phase with verification gates, deviation logs, and a final execution report.

Who is it for?

Developers with a signed-off ExecPlan or checklist who want gated phase execution and a documented verification report at the end.

Skip if: Exploratory coding without an approved plan or teams that do not need phase gates, deviation tracking, or formal execution reports.

When should I use this skill?

An ExecPlan or implementation checklist is approved and the agent should execute phases with verification gates and a final report.

What you get

Phase-by-phase execution report, verification matrix results, deviation log, blocker resolutions, and follow-up task list.

  • Execution report
  • Verification matrix
  • Deviation and blocker log

By the numbers

  • Verification matrix covers 5 checks: lint, type check, tests, build, and manual QA
  • Supports 2 execution modes: Batch and Interactive

Files

SKILL.mdMarkdownGitHub ↗

Execute Plan

Overview

Execute a pre-approved plan with strict adherence to scope, sequence, and verification. Treat the plan as a living document that records progress, findings, decisions, and outcomes as execution proceeds.

The input is typically: execute-plan docs/.plans/YYMMDD-HHmm-<plan-slug>/SUMMARY.md

Do not redesign the plan during execution. If ambiguity or blockers appear, stop and ask.

Workflow

Step 1: Initialize

1. Locate Plan

  • Confirm the plan path exists and is readable.
  • If a directory is provided, locate SUMMARY.md inside it.

2. Load Execution Context

  • Load only the project context relevant to the plan:
  • If docs/SUMMARY.md exists, read it first.
  • Load only task-relevant detail docs.
  • Prioritize Code Standard docs for implementation conventions.
  • If docs conflict with code or user intent, use the available input/question before broad changes.
  • Review the plan’s phase files, context/orientation notes, dependencies, acceptance criteria, idempotence/recovery notes, decision log, and open questions.
  • If an older plan is missing living-plan sections (Progress, Surprises & Discoveries, Decision Log, Outcomes & Retrospective), add those sections before execution when the plan is otherwise clear.

3. Select Execution Mode (Explicit Rule)

  • Default mode: Batch
  • Use Interactive when any of the following is true:
  • High-risk changes (auth, payments, migrations, security-critical logic)
  • Irreversible operations (data migrations, destructive scripts)
  • Unclear acceptance criteria
  • User explicitly requests checkpoints
  • If mode is unclear, ask once and proceed with user choice.

4. Find Next Pending Phase

  • First [ ] phase
  • If none, first [-] phase
  • If no pending/in-progress phases remain, go to final verification.

5. Critical Plan Sanity Check

  • Ensure each phase has:
  • clear objective
  • file targets
  • verification commands
  • observable acceptance criteria
  • If observable acceptance criteria are missing but can be inferred from explicit phase verification and exit criteria, add them to the phase before execution.
  • If essential details are missing or contradictory, stop and request clarification.

Step 2: Execute Per-Phase Loop

For each phase in order:

1. Skip Completed

  • If status is [x], continue to next phase.

2. Mark In Progress

  • Update phase status to [-] before making changes.
  • Add a timestamped Progress entry in SUMMARY.md describing the phase start.

3. Execute Exactly

  • Implement only the tasks defined in that phase.
  • Do not expand scope without approval.
  • Write the minimum code that satisfies the phase. No speculative features, no abstractions for single-use code, no error handling for impossible scenarios. See Simplicity first and Surgical changes rules below.
  • If implementation reveals a material surprise, record it under Surprises & Discoveries in SUMMARY.md.
  • If a decision is needed to stay within scope, record the decision and rationale under Decision Log before continuing.

4. Verify Phase

  • Run the phase-specific verification commands from the plan.
  • At minimum, run relevant tests/checks tied to touched files.
  • Record concise verification evidence in SUMMARY.md under Progress or the phase's requested evidence location.

5. Handle Failures

  • If verification fails:
  • Attempt focused fixes within phase scope.
  • Re-run verification.
  • If still failing or root cause is outside scope, stop and report blocker.

6. Mark Complete

  • Update phase status to [x] only after verification passes.
  • Add a timestamped Progress entry with the verification result and changed files for that phase.

7. Progress Report

  • Interactive mode: report and wait for confirmation before next phase.
  • Batch mode: report briefly and continue immediately.

Step 3: Final Verification

After all phases are complete:

1. Project-Wide Validation

  • Run full lint/type-check suite
  • Run all relevant tests (or full test suite if required by the plan)
  • Run build verification if applicable

2. Stabilize

  • Fix regressions introduced during execution.
  • Re-run failed checks until green or blocked.

3. Manual Validation Checkpoint

  • If user/manual QA is required, ask explicitly and pause:
  • Verified to accept
  • or provide feedback for follow-up iteration

4. Update Outcomes

  • Complete Outcomes & Retrospective in SUMMARY.md with final result, verification summary, approved deviations, and follow-ups.

Step 4: Completion Artifacts

1. Documentation Sync

  • If behavior/architecture/codebase expectations changed, update the docs artifacts.

2. Create Execution Report

  • File: docs/.plans/YYMMDD-HHmm-<plan-slug>/EXECUTION-REPORT.md
  • Include all required sections below.

3. Prepare Final Gate

  • Do not archive before final user confirmation. The user may choose Need verify, and execution must continue against the same plan path.

Step 5: Final Confirmation Gate

After completion artifacts are done, ask the user for a final confirmation using the input/question with exactly these options:

  • Confirm: End session
  • Need verify

Handle the selected option as follows:

1. `Confirm: End session`

  • Archive the plan folder to docs/.plans/archived/.
  • Announce: Execution complete. Report archived at docs/.plans/archived/YYMMDD-HHmm-<plan-slug>/EXECUTION-REPORT.md.
  • End the execution session.

2. `Need verify`

  • Allow the user to provide verification feedback/details.
  • Do not archive.
  • Continue the execution loop to address feedback, then re-run verification and completion steps as needed.

Execution Report Standard

EXECUTION-REPORT.md must use the following template: references/execution-report-template.md

Rules

  • Respect project standards: follow docs/ and related project docs.
  • Follow the plan strictly: no silent scope changes.
  • Stop on blocker: missing dependency, contradictory instructions, or unexplained failures.
  • No guessing: ask for clarification when uncertain.
  • Verify before complete: never mark phase done without passing checks.
  • Keep the plan alive: update progress, discoveries, decisions, and outcomes in SUMMARY.md as execution proceeds. Do not rely on chat history for important execution state.
  • Idempotency: prefer safe/re-runnable operations.
  • Simplicity first: Implement the minimum code that satisfies the phase's exit criteria. No features beyond what the plan asks for. No abstractions for single-use code. No configurability that wasn't requested. If you write 200 lines and it could be 50, rewrite it.
  • Surgical changes: Touch only what the phase requires. Don't "improve" adjacent code, comments, or formatting. Don't refactor things that aren't broken. Match existing style even if you'd do it differently. Only remove imports/variables/functions that _your_ changes orphaned — don't delete pre-existing dead code unless the plan asks for it. Every changed line should trace to a phase task.
  • Write artifacts in language same with the current session.

Related skills

How it compares

Use execute-plan when an approved checklist needs gated phase execution and a formal report instead of informal task-by-task coding without verification tracking.

FAQ

What modes does execute-plan support?

execute-plan supports Batch and Interactive modes for running an approved ExecPlan. Each mode records per-phase implementation details, verification command results, and notes in the final execution report.

What verification checks does execute-plan track?

execute-plan tracks lint, type check, tests, build, and manual QA in a verification matrix. Each check records pass or fail status with the command used, plus deviations, blockers, and follow-up tasks.

Is Execute Plan safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.