task-generate

A command that turns a discovery document into implementation tasks linked to Jira, a project-management system.

In plain words
What is it for?
Use it to create backlog files with goals, context, acceptance tests, and Jira or draft task IDs.
Why use it?
It gives a large feature a set of smaller, testable tasks and records unresolved questions instead of guessing about them.

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

Made for: Claude Code.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 405 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 $0.00017 $0.00405
Opus 5 $0.00009 $0.00202
Sonnet 5 $0.00003 $0.00081
Haiku 4.5 $0.00002 $0.00040

Measured 2d ago against content hash 40f97990b0c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-generate 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-generate.md · 26 lines

What it actually says

Generate tasks from the discovery doc backlog/discovery/$ARGUMENTS.md using templates/task.md.

Steps

  1. Read the discovery doc. If it doesn't exist, list available ones and ask which to use (or suggest /req-capture first).

    Tasks are written in English (the repo's only content language); each task's frontmatter records language: en.

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

  3. Slice the functional needs into tasks. Rules:

    • One verifiable outcome per task; split anything you couldn't implement in one OpenSpec change.
    • Each task gets a Goal (what & why), Context, and at least one Gherkin scenario per acceptance criterion, including one unhappy path. Every Then must be observable/testable.
    • Non-functional needs become acceptance criteria on the tasks they constrain, or their own task if cross-cutting.
    • Do NOT create tasks from Open questions — list them at the end as "blocked: needs answer".
  4. Task IDs are Jira keys. Show the user the proposed task list (title + one-line goal) and ask them to provide the Jira ID for each (e.g. PROJ-123). For tasks not yet created in Jira, assign draft IDs <project_key>-D01, -D02, ... and note they must be renamed when the real key exists.

  5. Write each task to backlog/tasks/<id>-<slug>.md with frontmatter filled: id, title, status: draft, discovery, priority (MoSCoW from the discovery's goals), language.

  6. Suggest /task-enrich <id> for the ones to refine, or /task-jira <id> to export.

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 · 26 lines · 17 tokens per session scan A 40f97990b0c7

Subscribe to this mod's changes

task-generate is a command published in the GitHub repository iolairus/borderlint (7 stars, last pushed 9d ago), licensed MIT. It adds 17 tokens to every session and 405 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.