Do
- 5.6k installs
- 89.6k repo stars
- Updated August 4, 2026
- thedotmack/claude-mem
do is an agent skill that executes phased implementation plans by orchestrating subagents for implementation, verification, anti-pattern checks, and gated commits.
About
The do skill makes an orchestrator agent execute phased plans by deploying subagents for all implementation work rather than coding directly. Each phase assigns one clear objective per subagent and requires evidence such as commands run, outputs, and files changed before advancing. Implementation subagents must copy patterns from documentation, cite unfamiliar API sources in code comments, and stop to verify when an API appears missing instead of inventing it. After each phase, separate Verification, Anti-pattern, and Code Quality subagents run the plan checklist, grep for known bad patterns, and review changes; a Commit subagent runs only after verification passes. Between phases, a Branch or Sync subagent pushes the working branch and prepares handoff context so the next phase can start fresh while retaining plan references. Fresh subagents are used when context is large or unclear. The skill pairs with make-plan for documentation-first planning and prevents skipped verification, undocumented parameters, and premature commits. Use when asked to execute, run, or carry out a plan created by make-plan.
- Orchestrator delegates all implementation work to subagents and only coordinates plus verifies completion.
- Implementation subagents must copy documented patterns and stop when APIs are not verified.
- Post-phase Verification, Anti-pattern, and Code Quality subagents run before any commit.
- Commit subagents run only after verification checklists pass or explicit orchestrator approval.
- Branch or Sync subagents push verified work and prepare the next phase handoff context.
Do by the numbers
- 5,623 all-time installs (skills.sh)
- +228 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #139 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
do capabilities & compatibility
- Capabilities
- deploy implementation subagents with single obje · require evidence before advancing to the next pl · run verification and anti pattern subagents afte · gate commits behind successful verification chec · push branches and prepare inter phase handoff co
- Use cases
- orchestration · planning · code review
What do says it does
COPY patterns from documentation, don't invent
npx skills add https://github.com/thedotmack/claude-mem --skill doAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 5.6k |
|---|---|
| repo stars | ★ 89.6k |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 4, 2026 |
| Repository | thedotmack/claude-mem ↗ |
How do agents carry out multi-phase plans without inventing APIs, skipping verification, or committing unproven changes?
Execute a phased implementation plan by deploying subagents for implementation, verification, anti-pattern checks, and commits only after proof.
Who is it for?
Orchestrator agents running plans produced by make-plan across multiple phases and fresh sessions.
Skip if: Skip for planning-only requests or single-step edits that do not need phased subagent execution.
When should I use this skill?
User asks to execute, run, or carry out a plan, especially one created by make-plan.
What you get
Each plan phase completed with subagent evidence, verification and anti-pattern checks passed, and commits only after proof.
- phase completion reports
- changed files
- command evidence
Files
../../../plugin/skills/do/SKILL.md
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Use do to execute an existing plan via subagents; use make-plan first when no phased plan exists yet.
FAQ
Does the orchestrator write code directly?
No. The orchestrator deploys Implementation subagents for work and only coordinates, routes context, and confirms checklist completion.
When are commits allowed?
Only after Verification subagents pass the phase checklist and optional orchestrator approval; otherwise do not commit.
What should happen if an API seems missing?
Implementation subagents must stop and verify against documentation instead of assuming the API exists or adding undocumented parameters.
Is Do safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.