task-new

A command for creating one implementation task directly in a project backlog, without first writing a discovery document.

In plain words
What is it for?
Use it to create a task with a goal, context, acceptance tests, edge cases, and either a Jira ID or draft ID.
Why use it?
It provides a structured task when the work is small enough to define in one short interview.

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/iolairus/borderlint/task-new
Clone the repo
git clone --depth 1 https://github.com/iolairus/borderlint

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 450 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 $0.00011 $0.00450
Opus 5 $0.00005 $0.00225
Sonnet 5 $0.00002 $0.00090
Haiku 4.5 $0.00001 $0.00045

Measured 2d ago against content hash 1dfa0c7ffb43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-new 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-new.md · 28 lines

What it actually says

Create one task in backlog/tasks/ from scratch using templates/task.md. $ARGUMENTS is a short title or topic; ask for it if missing. For initiatives that need several tasks or a requirements interview, redirect to /req-capture instead.

Steps

  1. Read workflow.yaml (jira.project_key, backlog.tasks_dir).

    The task is written in English (the repo's only content language); record language: en.

  2. Mini interview — ask only what's needed to fill the template, one round if possible:

    • Goal: what must exist or behave differently, and why.
    • Context: affected modules/specs, dependencies.
    • Acceptance criteria: at least one Gherkin scenario per criterion plus one unhappy path. Every Then must be observable/testable.
    • No invented answers: unknowns go to Notes & edge cases as open points.
  3. Task ID. Ask whether a Jira issue already exists for this:

    • Yes → use the real key (then the user probably wanted /task-import; offer it if they have ticket content to paste).
    • No → assign the next free draft ID <project_key>-Dnn (scan backlog/tasks/ for the highest Dnn). Note it must be renamed (file + frontmatter) when the real key exists.
  4. Cross-check against openspec/specs/ and existing tasks: contradiction or overlap → tell the user before writing.

  5. Write backlog/tasks/<id>-<slug>.md with frontmatter: id, title, status: draft, discovery: ~, priority (ask, MoSCoW), language.

  6. Suggest next: /task-enrich <id> to add edge cases and an estimate, then /task-jira <id> to export and create the issue in Jira (reminder: confirm the real key afterwards), or /opsx:propose if the task is ready to drive a change.

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 · 28 lines · 11 tokens per session scan A 1dfa0c7ffb43

Subscribe to this mod's changes

task-new is a command published in the GitHub repository iolairus/borderlint (7 stars, last pushed 9d ago), licensed MIT. It adds 11 tokens to every session and 450 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.