execute

A task-running command that breaks a natural-language request into smaller jobs and assigns each to a suitable specialist agent. It can coordinate several jobs at once and report what was completed.

In plain words
What is it for?
Use it for requests such as fixing an API bug, updating a user interface, adding tests, changing deployment files, or investigating a problem. It maps these jobs to backend, frontend, testing, operations, debugging, security, design, research, or architecture agents.
Why use it?
It removes the need to decide which agent should handle each part of a mixed development request. It also provides a review and summary when code changes are involved.

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/davidmatousek/tachi/execute
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/tachi

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 650 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 $0.00020 $0.00650
Opus 5 $0.00010 $0.00325
Sonnet 5 $0.00004 $0.00130
Haiku 4.5 $0.00002 $0.00065

Measured 2d ago against content hash 71be2f015d33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute 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 2d ago.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • execute — 100% identical, 0 lines differ
.claude/commands/execute.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Overview

Execute ad-hoc tasks with automatic agent assignment and parallel orchestration. Use for quick fixes, updates, and multi-file changes without the full triad workflow.

Input: Natural language task description (e.g., "Fix the OAuth bug and update docs")

Output: Completed tasks + Architect review (if code changes) + Execution summary


Agent Assignment

See Agent Registry for task-to-agent mapping.

Pattern Agent
api, endpoint, backend, database senior-backend-engineer
component, ui, react, frontend frontend-developer
test, validation, e2e tester
deploy, docker, ci/cd, infrastructure devops
debug, investigate, root cause debugger
security, vulnerability, auth security-analyst
design, mockup, ux ux-ui-designer
research, evaluate, best practice web-researcher
docs/architecture/ architect
docs/devops/ devops

Workflow

Step 1: Parse Tasks

Split user input by "and", ",", "then", ";" into discrete tasks. Classify each by keywords from the Agent Registry.

Step 2: Assign Agents

Map each task to primary agent using the Agent Registry table.

Step 3: Compute Waves

  • Wave 1: Tasks with no dependencies (can run in parallel)
  • Wave 2+: Tasks that depend on previous waves
  • Sequential keywords ("then", "after") create dependencies

Step 4: Execute

Launch agents in parallel within each wave using Task tool. Wait for wave completion before starting next wave.

Step 5: Architect Review

If any code was changed, invoke architect agent to review technical decisions.

Step 6: Summary

Report completed tasks, files modified, wave timings, and any issues.


Examples

Quick fix:

/execute Fix the login redirect bug and add a test for it

→ Wave 1: debugger (fix) → Wave 2: tester (test)

Parallel work:

/execute Add logging to the API, update the README

→ Wave 1: senior-backend-engineer + product-manager (parallel)

Read the full file on GitHub · 94 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. 2d ago First seen · 94 lines · 20 tokens per session scan A 71be2f015d33

Subscribe to this mod's changes

execute is a command published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 20d ago), licensed Apache-2.0. It adds 20 tokens to every session and 650 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 2026-08-30.