task

A guided intake workflow for turning a development request into a structured task plan for an autonomous task executor.

In plain words
What is it for?
Use it for multi-step tasks that need a written plan, provider and project details, risk notes, output location, and any required URLs or credentials.
Why use it?
It collects the missing decisions—such as the outcome, success checks, risks, tools, and deliverable—before work begins.

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/wingedguardian/genesis-agi/task
Clone the repo
git clone --depth 1 https://github.com/WingedGuardian/GENesis-AGI

Made for: Claude Code.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 855 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 $0.00033 $0.00855
Opus 5 $0.00016 $0.00428
Sonnet 5 $0.00007 $0.00171
Haiku 4.5 $0.00003 $0.00085

Measured 2d ago against content hash 9ca1cf666227, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/task.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Submission — Guided Intake

You are conducting a task intake interview following the TASK_INTAKE.md format (src/genesis/identity/TASK_INTAKE.md).

Process

  1. Read the user's request: $ARGUMENTS

  2. Triage first: Is this multi-step, time-consuming, background-appropriate? If not, handle inline — say so and do it directly.

  3. Gather requirements (one question at a time, don't over-interview):

    • Desired outcome and success criteria (specific + testable)
    • LLM provider preference (OpenAI/Anthropic/other) with SDK + env var + model
    • Risks and failure modes (specific, not vague)
    • Deliverable format and where output goes
    • If the outcome is a send-ready deliverable (report, deck, take-home, one-pager, proposal, document under the user's name): capture a Deliverable Frame — format, visual_style, authenticity_target, audience, what_leads, acceptance. Use the Gate-1 questions in .claude/skills/deliverable-builder/references/intake.md. This frame is un-recoverable after intake; the executor renders the result through the deliverable-builder skill and needs it.
    • Any URLs, file paths, API details, or credentials the executor needs
  4. Enter plan mode and write the plan to ~/.genesis/plans/

  5. Plan structure — task_submit enforces these four sections (rejects if missing):

    • ## Requirements
    • ## Steps (from executor CC session's perspective)
    • ## Success Criteria (testable by the executor)
    • ## Risks and Failure Modes (specific)

    Also include these sections (best practice, caught by the LLM plan reviewer):

    • ## Context
    • ## Deliverable Format
    • ## Deliverable Frame (send-ready deliverables ONLY — its presence triggers the deliverable-builder pipeline; omit for code/data/internal tasks)
    • ## Quality Checks (achievable in the executor's environment)
    • ## Constraints
  6. After user approves the plan: a. Call intake_complete() MCP tool to generate a one-time intake token b. Call task_submit(plan_path=<path>, description=<description>, intake_token=<token>) MCP tool with the token from step 6a The token enforces that submissions went through this intake process. It expires after 2 hours and can only be used once.

Read the full file on GitHub · 69 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 · 69 lines · 33 tokens per session scan A 9ca1cf666227

Subscribe to this mod's changes

task is a command published in the GitHub repository WingedGuardian/GENesis-AGI (93 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 855 once invoked, about $0.0002 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.