Skills thedotmack claude-mem

do

Use it when:
You have a phased plan, such as one from make-plan, and want it carried out.
It does:
Stays a coordinator and hands all the work to subagents: one implements each phase, others verify, check anti-patterns and review.
You get:
One commit per phase that passed its checks, pushed to your working branch.
Needs:
An agent that can start subagents.
Won't:
Move to the next phase, or commit, until a subagent's evidence shows the phase is done.

Commits each phase once it passes verification and pushes to your working branch between phases.

TL;DR

The main agent does no work itself except routing context and checking each subagent's report against the plan. Every subagent gets one objective and must report evidence: commands run, outputs and files changed. In each phase an implementation subagent copies patterns from the documentation, cites sources for unfamiliar APIs and stops to verify when an API seems missing rather than assuming it exists. After the phase, separate subagents run its verification checklist, grep for the plan's known bad patterns and review code quality, and a commit subagent commits only if verification passed. Between phases a branch subagent pushes to the working branch and prepares a handoff, so the next phase's subagents start fresh but know the plan.

Summarizes the skill at 24802b1.

npx skills add https://github.com/thedotmack/claude-mem --skill do
Total Downloads
7,300 on skills.sh, Nov 9, 2026
Repo stars
114,993 thedotmack/claude-mem
First seen
Feb 24, 2026 on skills.sh
Weekly Downloads
152
+48% over the 8 weeks to Nov 9
Weekly values
Week toInstalls
Sep 21103
Sep 2896
Oct 592
Oct 1291
Oct 19128
Oct 26116
Nov 2133
Nov 9152
Category

Test-first work, implementation from specs, git hygiene and scope control.

Build agents, orchestrate workers and give agents memory.

Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.

Type

A multi-step process the agent follows: interview, debug, run a TDD loop, review.

Effect

Its own steps change something outside your machine: post, send, deploy, provision, file issues, drive a website, or upload data to a service.

Needs

Relies on the agent being able to spawn subagents.

Publisher

Everyone else. Unverified vendor claims default to community.

Topics

SKILL.md

From thedotmack/claude-mem at 24802b1. Checked daily, last changed Nov 6, 2026.

Frontmatter
name: do
description: Execute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.

Do Plan

You are an ORCHESTRATOR. Deploy subagents to execute all work. Do not do the work yourself except to coordinate, route context, and verify that each subagent completed its assigned checklist.

Execution Protocol

Rules
  • Each phase uses fresh subagents where noted (or when context is large/unclear)
  • Assign one clear objective per subagent and require evidence (commands run, outputs, files changed)
  • Do not advance to the next step until the assigned subagent reports completion and the orchestrator confirms it matches the plan
During Each Phase

Deploy an "Implementation" subagent to:

  1. Execute the implementation as specified
  2. COPY patterns from documentation, don't invent
  3. Cite documentation sources in code comments when using unfamiliar APIs
  4. If an API seems missing, STOP and verify — don't assume it exists
After Each Phase

Deploy subagents for each post-phase responsibility:

  1. Run verification checklist — Deploy a "Verification" subagent to prove the phase worked
  2. Anti-pattern check — Deploy an "Anti-pattern" subagent to grep for known bad patterns from the plan
  3. Code quality review — Deploy a "Code Quality" subagent to review changes
  4. Commit only if verified — Deploy a "Commit" subagent only after verification passes; otherwise, do not commit
Between Phases

Deploy a "Branch/Sync" subagent to:

  • Push to working branch after each verified phase
  • Prepare the next phase handoff so the next phase's subagents start fresh but have plan context

Failure Modes to Prevent

  • Don't invent APIs that "should" exist — verify against docs
  • Don't add undocumented parameters — copy exact signatures
  • Don't skip verification — deploy a verification subagent and run the checklist
  • Don't commit before verification passes (or without explicit orchestrator approval)