task-import

A command that turns pasted Jira ticket details into a task file in a project's backlog. Jira is a tool for tracking issues and planned work.

In plain words
What is it for?
Use it to import a Jira issue into `backlog/tasks/`, normalize its description and acceptance criteria, and handle existing task files or mismatched project keys.
Why use it?
It preserves the ticket's meaning in the repository without fetching from Jira or inventing missing details.

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

Made for: Claude Code.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 515 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 $0.00013 $0.00515
Opus 5 $0.00006 $0.00258
Sonnet 5 $0.00003 $0.00103
Haiku 4.5 $0.00001 $0.00052

Measured 2d ago against content hash 371c6799bd42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-import 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-import.md · 30 lines

What it actually says

Import the existing Jira ticket $ARGUMENTS (a real Jira key like PROJ-123) into backlog/tasks/ using templates/task.md. The ticket content is always pasted by the user — never fetch it from Jira or invent it.

Steps

  1. Read workflow.yaml (jira.project_key, backlog.tasks_dir). If $ARGUMENTS is missing or doesn't look like a Jira key, ask for it. If the key's project prefix differs from jira.project_key, warn but don't block.

  2. If backlog/tasks/ already has a file for that key, show it and ask whether to update it from a fresh paste or abort.

  3. Ask the user to paste the ticket content: title, description, acceptance criteria, and any comments worth keeping. Plain text or Jira wiki markup, as-is.

    The task file is written in English (the repo's only content language) regardless of the pasted ticket's language — translate when needed and record language: en in the frontmatter.

  4. Normalize the paste into templates/task.md — restructure, don't rewrite meaning:

    • Frontmatter: id = the real Jira key, status: draft, discovery: ~ (no discovery doc), priority only if the ticket states one.
    • Ticket description → Goal (what & why) and Context (background, affected areas).
    • Acceptance criteria → Gherkin scenarios. Convert only what the ticket actually says; if a criterion isn't testable as written, keep it verbatim under Notes & edge cases flagged as needs clarification — do NOT invent Given/When/Then.
    • Anything the ticket leaves open goes to Notes & edge cases as open points.
    • Add one line to Context: Imported from Jira <key> on <date>.
  5. Write backlog/tasks/<key>-<slug>.md and run the task-reviewer subagent on it.

  6. Suggest next, based on the review:

    • Findings or thin scenarios → /task-enrich <key> to fill edge cases and estimate.
    • Solid as imported → /opsx:propose <change-name> referencing the task.
    • Never suggest /task-jira here — the ticket already exists in Jira.
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 · 30 lines · 13 tokens per session scan A 371c6799bd42

Subscribe to this mod's changes

task-import is a command published in the GitHub repository iolairus/borderlint (7 stars, last pushed 9d ago), licensed MIT. It adds 13 tokens to every session and 515 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.