task_complete

A command workflow for completing software tasks through specialised subagents. It requires an orchestrator to create a task folder, record the request, and delegate the work in sequence.

In plain words
What is it for?
Use it to organise multi-step feature work, assign project-context gathering, and coordinate subagents through a documented task directory.
Why use it?
It separates planning, investigation, implementation, and review between dedicated agents. The orchestrator itself is not supposed to edit code or inspect implementation files.

Command

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/codeoutin/claude-code-agency/task_complete
Clone the repo
git clone --depth 1 https://github.com/codeoutin/claude-code-agency
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,438 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 $0.00000 $0.01438
Opus 5 $0.00000 $0.00719
Sonnet 5 $0.00000 $0.00288
Haiku 4.5 $0.00000 $0.00144

Measured 2d ago against content hash a731c7a9d787, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task_complete 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.

commands/task_complete.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Complete Command - Production-Ready Feature Implementation

YOUR ROLE: ORCHESTRATOR ONLY

YOU ARE THE ORCHESTRATOR. You must NOT write any code, read files for implementation, or make any edits yourself. Your ONLY job is to call the Task tool to spawn specialized subagents in sequence. If you find yourself writing code or editing files, STOP — you are doing it wrong. Delegate everything.


SETUP

Run this bash command to create the task directory:

TIMESTAMP=$(date +"%Y-%m-%d-%H-%M-%S") && mkdir -p "./claude-tasks/${TIMESTAMP}_task" && echo "./claude-tasks/${TIMESTAMP}_task"

From the output, derive a 2-4 word slug from the task description (e.g. invoice-redesign, auth-fixes, timer-system) and rename:

mv "./claude-tasks/${TIMESTAMP}_task" "./claude-tasks/${TIMESTAMP}_{SLUG}"

Set TASK_DIRECTORY to the final path. Save the task description:

echo "$ARGUMENTS" > "$TASK_DIRECTORY/TASK.md"

STEP 1 — CALL Task tool: tc-context-gatherer

IMMEDIATELY call the Task tool with these parameters. Do NOT skip this.

  • subagent_type: tc-context-gatherer
  • description: "Gather project context"
  • prompt:
    Task directory: {TASK_DIRECTORY}
    Task: {TASK_DESCRIPTION}
    
    Analyze the complete codebase. Save comprehensive context to {TASK_DIRECTORY}/context.md.
    Capture baseline lint and build metrics. Save to {TASK_DIRECTORY}/validation-tracking.json with this shape:
    { "baseline": { "lint_errors": N, "build_success": true/false, "timestamp": "..." }, "current": null, "validation_passed": false }
    

BLOCKING GATE: Do NOT proceed to Step 2 until the Task tool call returns.


STEP 2 — CALL Task tool: tc-task-planner

IMMEDIATELY call the Task tool with these parameters.

  • subagent_type: tc-task-planner
  • description: "Create implementation plan"
  • prompt:
    Task directory: {TASK_DIRECTORY}
    Task: {TASK_DESCRIPTION}
    
    Read {TASK_DIRECTORY}/context.md. Create a detailed, file-level implementation plan.
    Save to {TASK_DIRECTORY}/plan.md.
    

Read the full file on GitHub · 182 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 · 182 lines · 0 tokens per session scan A a731c7a9d787

Subscribe to this mod's changes

task_complete is a command published in the GitHub repository codeoutin/claude-code-agency (41 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,438 tokens. 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.