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-goalgit 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 | $0.00328 |
| Opus 5 | $0.00000 | $0.00164 |
| Sonnet 5 | $0.00000 | $0.00066 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
extend-goal 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 3d 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
Extend Goal
Description
Extend an existing goal — broaden or add to its objective, building on top of what the earlier /goal run already implemented.
Usage
/extend-goal
Behavior
Loads and executes the extend-goal workflow from .ab-method/core/extend-goal.md
This workflow will:
- Identify the goal and read its
goal.md+progress-tracker.md, then confirm the real code state - Always invoke
grill-with-docsto pin down the extension, a verifiable new measurable end state, updated feedback loops, and new constraints - Update
goal.mdin place — extended objective, new end state, plus anAlready implementedsection so the loop builds on existing work - Keep the same
progress-tracker.md— its Notes carry forward, never reset
Workflow Details
- Always grill —
grill-with-docsruns on every invocation - Update in place — one
goal.mdper goal; never a second file - Build on, do not rebuild — the
Already implementedsection tells the/goalloop what to keep - No checklist —
progress-tracker.mdis a notes log; the loop runs until the measurable end state holds
Examples
/extend-goal
# Reads the existing goal, grills for the extension,
# rewrites goal.md to target the extended objective
Alternative Usage
/ab-master extend-goal
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.
- 3d ago First seen · 37 lines · 0 tokens per session scan A add84c101def
extend-goal 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 328 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
git
Git operations with intelligent commit messages and workflow optimization.
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.