executing-plans
Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead.
GanyuanRan · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add GanyuanRan/Aegis --skill executing-plans技能说明
name: executing-plans description: "Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead."
Executing Plans
Overview
Load plan, review critically, execute all tasks, report when complete.
Announce at start: "I'm using the executing-plans skill to implement this plan."
For non-trivial execution, include Aegis Visibility: briefly tie the active
slice to its plan, checkpoint, drift or verification boundary. At completion,
pass plan adherence, evidence, complexity and residual risk to
verification-before-completion for the unified receipt.
If subagents are available and the plan has genuinely independent tasks,
prefer subagent-driven-development; lack of subagent support does not block
inline execution. Same-task agents share one workspace, and the coordinator
remains the only Git mutation owner.
The Process
Step 1: Load and Review Plan
- Read plan file
- If the plan or active checkpoint includes an
Execution Readiness View, read it before implementation and compare the plan against its intent lock, scope fence, baseline lock, owner / contract constraints, compatibility boundary, retirement boundary, test obligations, review gates, drift / rewind rules, and evidence required before completion. - Review critically - identify any questions or concerns about the plan
- If the view contradicts the plan, baseline, or current worktree evidence, return to plan review or refresh the advisory handoff before editing.
- Run the TDD Route Guard before implementation: confirm
Mode,Decision,Strict authority, strict signals, light eligibility,Test posture, and verification. Strict steps require either an explicit user/project request or a recorded auto decision; plan approval or risk labels alone are not authority. An off-mode missing record may be repaired only asMode: off / Decision: skippedwithout loading TDD. Missing/unsupported auto decisions return to plan review. An auto-light record is unsupported when any strict signal is present or when its tiny/low-risk/single-owner/no-behavior-change proof is incomplete. OnlyDecision: strictwith recorded strict authority may authorize steps namedWrite failing test,Verify RED,GREEN, orREFACTOR. Do not inferstrictduring execution. - If concerns: Raise them with your human partner before starting
- Before the first write, capture
TaskStartSnapshot: root,HEAD, branch or detached state, upstream divergence, staged/unstaged/untracked paths, active Git operations, andgit worktree list --porcelain. Preserve task-preexisting state; do not stash, reset, clean, or commit it. - Reuse the current branch unless rules require independent history or another goal owns it. If justified, switch/create it in the current workspace when safe; a worktree still requires concurrent checkout or blocking dirty state.
- If no concerns: Create TodoWrite and proceed
Step 1.5: Long-Task Checkpoint Setup
If the plan has multiple tasks, may span sessions, or includes architecture / contract / workflow changes:
- Announce: "I'm using the long-task-continuation skill to keep this plan checkpointed and drift-aware."
- Load aegis:long-task-continuation.
- Create the initial checkpoint from the plan:
- current todo
- active task
- completed tasks
- evidence refs
- blockers
- next step
- Before each task, restate the current checkpoint.
- After each task, update checkpoint, evidence refs, and drift check.
Before a verification-driven unplanned edit, read retained PatchShape,
CanonicalOwner, UpwardDrillSignal, outcome, and evidence refs. Route their
comparison with the candidate to systematic-debugging before editing; it
decides whether the directions converge. A proven independent canonical-owner
root stays on the normal plan path.
Step 2: Execute Tasks
For each task:
-
Mark as in_progress
-
Follow each step exactly (plan has bite-sized steps)
-
Before any new source-code path is added by a task, restate the plan's
Change Necessityor create a compact one if the plan failed to carry it forward. Plan approval is not by itself proof that a new helper, small guard, new branch, fallback, adapter, or owner is necessary.Change Necessity: - User-visible need: - No-change / non-code option: - Why code change is necessary: - Minimum change boundary: - Decision: no-change | docs/config-only | code-change | needs-clarificationIf the decision is not
code-change, pause execution and return to plan review instead of editing. If the decision iscode-change, carry the minimum boundary into the edit and verification scope. -
Before any non-trivial source edit, run the plan's
Pre-Edit Complexity Checkor create a compact one:Use
using-aegis/references/complexity-governance.mdfor shared artifact classes, pressure signals, andover-budgethandling.Complexity Budget: - Artifact class: - Target files / artifacts: - Current pressure: - Projected post-change pressure: - Budget result: within-budget | at-risk | over-budget - Planned governance: Pre-Edit Complexity Check: - Target edit file: - Existing pressure signal: - Safer edit boundary: - Decision: edit-in-place | extract helper | add owner file | split task | pause for plan update Pre-Edit Owner-Fit Decision: - Edit intent: wiring-only | move-out / extract-first | local-fix-without-new-responsibility | new-responsibility | emergency / compatibility patch - Owner fit: - Safer edit boundary: - Decision: edit-in-place | extract helper | add owner file | split task | pause for plan updateIf the check contradicts the plan's file boundary, pause and return to plan