task

A workflow for creating tracked development tasks with a specification and progress records. It supports behavior changes, bug fixes, refactors, infrastructure work, general work, and quality-assurance tasks.

In plain words
What is it for?
Creating task folders, assigning the next available number, gathering requirements, and recording work for bugs, features, refactors, infrastructure, or testing.
Why use it?
It turns a loosely described request into a numbered task with the right questions for its type. This makes the expected outcome and progress easier to follow.

Skill for Claude CodeCodex

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 skills/rakovi4/continue-framework/task
Any agent
npx skills add rakovi4/continue-framework --skill task
Clone the repo
git clone --depth 1 https://github.com/rakovi4/continue-framework

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 646 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 $0.00040 $0.00646
Opus 5 $0.00020 $0.00323
Sonnet 5 $0.00008 $0.00129
Haiku 4.5 $0.00004 $0.00065

Measured 2d ago against content hash 307ba3db5414, 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/skills/task/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/task - Create Task

Input

  • type (optional): behavior-change, bugfix, refactor, infra, general, or qa
  • title (optional): short title of two to five words

Workflow

  1. List every directory under ProductSpecification/tasks/ and ProductSpecification/tasks/done/. Extract and show every leading integer; the next global task number is the maximum plus one, or 1 when none exist. Before creation, verify no folder in either location starts with that number.
  2. Parse the canonical type and title. If either is missing, ask for it.
  3. Create ProductSpecification/tasks/{N}-{type}-{slug}/, with a lowercase, hyphenated slug of at most five words.
  4. Gather the type-specific spec in two or three rounds:
    • behavior-change: problem, current and expected observable behavior, constraints, and likely key files; do not pre-plan TDD steps.
    • bugfix: symptoms, observed versus expected behavior, environment, frequency, captured errors, and reproduction; do not ask for a cause, solution, affected layers, or key files.
    • refactor: structural problem, behavior-preserving outcome, constraints, and likely key files; do not pre-plan implementation steps.
    • infra: problem, intended infrastructure-as-code outcome, constraints, likely files, and bounded direct work units. Never plan manual remote changes.
    • general: problem, intended outcome, constraints, likely files, and bounded direct work units.
    • qa: why and when to run the checklist, target environment, session duration, and numbered one-line cases; omit affected layers and key files.
  5. Generate spec.md and progress.md from .claude/templates/task/creation-formats.md:
    • behavior-change: design then steps discovery; discovery inserts TDD.
    • bugfix: root-cause-first discovery; discovery inserts TDD.
    • refactor: design and discovery insert direct behavior-preserving steps.
    • infra and general: design, then one direct step per Work item.
    • qa: design, then one manual checkbox per case.
  6. Show both files for review, then commit them as task: spec (Task {N}, {title}).

Read the full file on GitHub · 53 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 · 53 lines · 40 tokens per session scan A 307ba3db5414

Subscribe to this mod's changes

task is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 646 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.