ab-start-task

A workflow for handing an existing, well-defined task to autonomous agents until it is finished. TDD means test-driven development, where tests help guide the implementation.

In plain words
What is it for?
Use it when you want an agent to run a task through completion while updating the tracker and producing reviewable commits.
Why use it?
It breaks the remaining work into missions, records progress, and requires a commit after each mission that passes its checks.

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/ayoubben18/ab-method/ab-start-task
Any agent
npx skills add ayoubben18/ab-method --skill ab-start-task
Clone the repo
git clone --depth 1 https://github.com/ayoubben18/ab-method

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 135 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 $0.00055 $0.00135
Opus 5 $0.00028 $0.00068
Sonnet 5 $0.00011 $0.00027
Haiku 4.5 $0.00006 $0.00014

Measured 2d ago against content hash 950bbf468660, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ab-start-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.

.agents/skills/ab-start-task/SKILL.md · 11 lines

What it actually says

This skill runs the AB Method start-task workflow.

Follow the workflow defined in .ab-method/core/start-task.md exactly — it contains the full process, output format, and rules.

Before doing anything, check .ab-method/structure/index.yaml. It defines where this workflow reads from and writes to. Paths are user-configurable; never hardcode them.

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 · 11 lines · 55 tokens per session scan A 950bbf468660

Subscribe to this mod's changes

ab-start-task is a skill published in the GitHub repository ayoubben18/ab-method (187 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 135 once invoked, about $0.0003 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.