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/extend-taskgit 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 | $0.00498 |
| Opus 5 | $0.00000 | $0.00249 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
extend-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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extend Task
Description
Add new missions to an existing task after initial missions have been completed. Useful when requirements change or new features need to be added to an ongoing task.
Usage
/extend-task
Behavior
Loads and executes the extend-task workflow from .ab-method/core/extend-task.md
This workflow will:
- Select a task to extend
- Review current mission progress
2b. Surface any open unresolved questions (
⚠️ UQ-n) — this is where a parked question gets answered: the workflow grills the answer, swaps theTODO(UQ-n)placeholder (or plans real missions if it's more than a seam swap), and marks the entryRESOLVED - Gather requirements for new missions (grills if vague)
- Append the new missions as one-line entries in
progress-tracker.md(no mission docs) - Run
critique-planon the new missions — the pre-implementation domain critic pushes back only on genuine conflicts before you confirm - Reopen the task if it was
Completed— and, if it belongs to a roadmap, reopen itsroadmap.mdentry too (status: done → pending) so a/start-roadmapre-run picks up the new work in dependency order
Workflow Details
The extend-task workflow provides:
- Task Selection - Choose which task to extend
- Progress Review - See what missions are already completed
- Mission Planning - Define new missions to add
- Context Preservation - Maintain technical context from existing missions
- Progress Tracking - Update
progress-tracker.mdwith new missions (one-line entries, no separate mission docs) - Roadmap-aware - If the task is part of a roadmap, reopening it updates
roadmap.mdso/start-roadmapre-runs the extended work in dependency order - Optional Parallel Groups - Independent new missions can be tagged
[pp-x](or join a pending group) for concurrent subagent execution — only with the user's explicit yes
Examples
/extend-task
# Selects a task and adds new missions
# Creates detailed mission documents
# Updates progress tracker with additional missions
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 · 47 lines · 0 tokens per session scan A 8e63f3ef4eab
extend-task 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 498 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.