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.
npx agentmods add commands/ayoubben18/ab-method/create-task-from-handoffgit clone --depth 1 https://github.com/ayoubben18/ab-methodWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00395 |
| Opus 5 | $0.00000 | $0.00198 |
| Sonnet 5 | $0.00000 | $0.00079 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
create-task-from-handoff 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.
What it actually says
Create Task From Handoff
Description
Resume a handoff — a side-topic that was captured mid-grill via the handoff skill — and turn it into a test-driven task. The bridge between two grilling sessions.
Usage
/create-task-from-handoff [handoff-slug]
Pass a slug to resume a specific handoff from docs/handoffs/. Omit it to pick from the pending list.
Behavior
Loads and executes the create-task-from-handoff workflow from .ab-method/core/create-task-from-handoff.md
This workflow will:
- Locate the handoff (by slug, or by listing
docs/handoffs/) - Absorb its context — treat everything it already settled as given
- Continue the grill via
grill-with-docs, driving only the branches the handoff left open - Hand off to the standard create-task flow (project analysis → missions →
tdd) - Retire the handoff once the task document exists
Workflow Details
- A handoff is a paused grill — resume it, don't restart it
- Reuses
create-taskwholesale from project analysis onward - Always grill, always TDD — same guarantees as
/create-task
How handoffs get created
During any grilling session, when a tangent emerges that deserves its own task, invoke the handoff skill to capture it under docs/handoffs/ — without derailing the current grill. Resume it later with this command.
Examples
/create-task-from-handoff rate-limit-redis-vs-token-bucket
# Resumes that specific handoff and grills the open branches
/create-task-from-handoff
# Lists pending handoffs and asks which to resume
Alternative Usage
/ab-master create-task-from-handoff
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.
- 2d ago First seen · 44 lines · 0 tokens per session scan A 91bd1bb35a58
create-task-from-handoff is a command published in the GitHub repository ayoubben18/ab-method (187 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 395 tokens. 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.
Other commands, from other repositories
tdd-requirements
TDD開発の要件整理を行います。機能要件を明確化し、テスト駆動開発のための準備を行います。.
go-test
Go TDD workflow with table-driven tests.
pm-auto-design2dev
設計レビューから実装完了まで完全自動化（設計レビュー→作業計画→TDD実装）.
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.
execute-plan
Execute an implementation plan methodically with TDD and continuous validation.
tdd
强制执行测试驱动开发工作流。首先搭建接口，生成测试，然后从实现能通过测试的最小代码。确保 80%+ 的覆盖率。.