amby.tasks

A command that turns a feature plan into an ordered checklist of small development tasks. It groups work into setup, foundations, user stories, and final cleanup.

In plain words
What is it for?
Use it to generate tasks.md for a planned feature and guide its implementation.
Why use it?
It makes dependencies and priorities visible before coding begins, including which tasks can run in parallel. It does not implement the feature.

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/ambystechcom/ambykit/amby.tasks
Clone the repo
git clone --depth 1 https://github.com/ambystechcom/AmbyKit

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 345 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 $0.00012 $0.00345
Opus 5 $0.00006 $0.00172
Sonnet 5 $0.00002 $0.00069
Haiku 4.5 $0.00001 $0.00034

Measured 2d ago against content hash cfc094948374, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

amby.tasks 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/amby.tasks.md · 23 lines

What it actually says

Act as the Tech Lead in @.amby/roles/tech-lead.md and say so in your first line. If $ARGUMENTS contains --as <id>, use @.amby/roles/<id>.md instead; if that file is missing, stop and list the files in .amby/roles/.

Generate tasks.md for feature $ARGUMENTS (default: the current feature).

Context: read that feature's plan.md (and spec.md for story IDs/priorities/dependencies).

  1. Write tasks following @.amby/templates/tasks.md as checkbox lines: - [ ] [T###] [P?] [US#] description (file/path).
  2. Group into phases: Setup → Foundational → User stories (by priority) → Polish. Enforce the gate: no user-story task before Foundational completes.
  3. Order tasks by the story dependency graph (depends-on/blocked-by) and priority. Mark independent tasks [P]. Tag each task with its [US#]. End each story group with a checkpoint.
  4. Give every task a stable T### id and a concrete file path.

Do not start implementing. Keep descriptions to one line each.

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 · 23 lines · 12 tokens per session scan A cfc094948374

Subscribe to this mod's changes

amby.tasks is a command published in the GitHub repository ambystechcom/AmbyKit (2 stars, last pushed 7d ago), licensed MIT. It adds 12 tokens to every session and 345 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.