execute-task

A command for running one planned task after checking its status and dependencies. It chooses a suitable helper agent and records the task's progress.

In plain words
What is it for?
Use it to execute one task from a plan, update its status, delegate the work, and document what happened.
Why use it?
It prevents tasks from running too early, running twice, or ending without a clear result. It also keeps a record of important outcomes and problems.

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/e0ipso/drupal-bridge-mcp/execute-task
Clone the repo
git clone --depth 1 https://github.com/e0ipso/drupal-bridge-mcp

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,762 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 $0.00010 $0.01762
Opus 5 $0.00005 $0.00881
Sonnet 5 $0.00002 $0.00352
Haiku 4.5 $0.00001 $0.00176

Measured 2d ago against content hash ec3492bedebe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute-task 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.

.claude/commands/tasks/execute-task.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Single Task Execution

You are responsible for executing a single task within a plan while maintaining strict dependency validation and proper status management. Your role is to ensure the task is ready for execution, deploy the appropriate agent, and track execution progress.

Use your internal Todo task tool to track the execution of all parts of the task, and the final update of noteworthy items during execution. Example:

  • Validate task: file, status, and dependencies.
  • Select the most appropriate sub-agent.
  • Set task status to in-progress.
  • Delegate task implementation to the sub-agent.
  • Update task status to completed or failed.
  • Update the task file with noteworthy events during execution.

Critical Rules

  1. Never skip dependency validation - Task execution requires all dependencies to be completed
  2. Validate task status - Never execute tasks that are already completed or in-progress
  3. Maintain status integrity - Update task status throughout the execution lifecycle
  4. Use appropriate agents - Match task skills to available sub-agents
  5. Document execution - Record all outcomes and issues encountered

Input Requirements

  • Plan ID: $1 (required)
  • Task ID: $2 (required)
  • Task management directory structure: /
  • Dependency checking script: .ai/task-manager/config/scripts/check-task-dependencies.cjs

Input Validation

First, validate that both arguments are provided:

if [ -z "$1" ] || [ -z "$2" ]; then
    echo "Error: Both plan ID and task ID are required"
    echo "Usage: /tasks:execute-task [plan-ID] [task-ID]"
    echo "Example: /tasks:execute-task 16 03"
    exit 1
fi

Execution Process

1. Plan and Task Location

Locate the plan directory using the established find pattern:

PLAN_ID="$1"
TASK_ID="$2"

# Find plan directory
PLAN_DIR=$(find .ai/task-manager/{plans,archive} -type d -name "${PLAN_ID}--*" 2>/dev/null | head -1)

if [ -z "$PLAN_DIR" ]; then
    echo "Error: Plan with ID ${PLAN_ID} not found"
    echo "Available plans:"
    find .ai/task-manager/plans -name "*--*" -type d | head -5
    exit 1
fi

echo "Found plan: $PLAN_DIR"

Read the full file on GitHub · 259 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 · 259 lines · 0 tokens per session scan A ec3492bedebe

Subscribe to this mod's changes

execute-task is a command published in the GitHub repository e0ipso/drupal-bridge-mcp (5 stars, last pushed 9mo ago), licensed MIT. It adds 10 tokens to every session and 1,762 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 2026-08-31.