do

A multi-agent task command that coordinates flexible workflows while limiting work to the approved task and requiring user approval at key planning stages.

In plain words
What is it for?
Use it for focused, small-step implementation work where requirements and the execution plan must be approved before agents make changes.
Why use it?
It prevents agents from adding unrequested work and makes complex changes easier to control and review.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/xsaven/vector-memory-mcp/do
Clone the repo
git clone --depth 1 https://github.com/Xsaven/vector-memory-mcp

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,676 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.04676
Opus 5 $0.00010 $0.02338
Sonnet 5 $0.00004 $0.00935
Haiku 4.5 $0.00002 $0.00468

Measured yesterday against content hash 2f8568f57584, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

do scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/do.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Iron Rules

Zero-distractions (CRITICAL)

ZERO distractions - implement ONLY specified task from $ARGUMENTS. NO creative additions, NO unapproved features, NO scope creep.

  • why: Ensures focused execution and prevents feature drift
  • on_violation: Abort immediately. Return to approved plan.

Approval-gates-mandatory (CRITICAL)

User approval REQUIRED at Requirements Analysis gate and Execution Planning gate. NEVER proceed without explicit confirmation.

  • why: Maintains user control and prevents unauthorized execution
  • on_violation: STOP. Wait for user approval before continuing.

Atomic-tasks-only (CRITICAL)

Each agent task MUST be small and focused: maximum 1-2 files per agent invocation. NO large multi-file changes.

  • why: Prevents complexity, improves reliability, enables precise tracking
  • on_violation: Break task into smaller pieces. Re-plan with atomic steps.

No-improvisation (CRITICAL)

Execute ONLY approved plan steps. NO improvisation, NO "while we're here" additions, NO proactive suggestions during execution.

  • why: Maintains plan integrity and predictability
  • on_violation: Revert to last approved checkpoint. Resume approved steps only.

Execution-mode-flexible (HIGH)

Execute agents sequentially BY DEFAULT. Allow parallel execution when: 1) tasks are independent (no file/context conflicts), 2) user explicitly requests parallel mode, 3) optimization benefits outweigh tracking complexity.

  • why: Balances safety with performance optimization
  • on_violation: Validate task independence before parallel execution. Fallback to sequential if conflicts detected.

Read the full file on GitHub · 329 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 329 lines · 21 tokens per session scan A 2f8568f57584

Subscribe to this mod's changes

do is a command published in the GitHub repository Xsaven/vector-memory-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 21 tokens to every session and 4,676 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.