A workflow for continuing a paused software task from its saved progress tracker. It identifies the next unfinished mission and works through it using TDD, or test-driven development: write a failing test, make it pass, then improve the code.

Resuming unfinished implementation work, loading the relevant project context, running the next mission, and reviewing the final code with several critics.

It avoids losing context between work sessions and shows exactly what remains. Tests and short technical summaries provide a persistent record of progress.

resume-task — Command by ayoubben18

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/ayoubben18/ab-method/resume-task

Clone the repo

git clone --depth 1 https://github.com/ayoubben18/ab-method

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 414 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00414
Opus 5	$0.00000	$0.00207
Sonnet 5	$0.00000	$0.00083
Haiku 4.5	$0.00000	$0.00041

Measured 2d ago against content hash f7f862e54d1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

resume-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.

.claude/commands/resume-task.md · 41 lines

What it actually says

Resume Task

Description

Resume an existing task from where it was paused, continuing with the next incomplete mission.

Usage

/resume-task

Behavior

Loads and executes the resume-task workflow from .ab-method/core/resume-task.md

This workflow will:

Identify the task and read its progress-tracker.md (single source of truth — there are no mission docs)
Show progress: which missions are done, which is next
Load UBIQ + CONTEXT + tech-stack + patterns + ADRs for the next mission
Run the next mission through the tdd skill (red-green-refactor)
Append a tight technical summary on completion
Run review-implementation after the last mission (interactive) — three critics (cleaner-architecture, slop-defender, reusability-inspector) on the task diff; findings presented for you to apply before status → Completed

Workflow Details

The progress tracker carries the mission list and per-mission technical summaries from prior sessions — that's the entire context
Tests + summaries are the persistent artifacts across sessions
Always TDD via the tdd skill, never skip it
Group-aware resume — if the next mission carries a [pp-x] tag, the remaining missions in that group are offered as one concurrent subagent batch (the user can still choose sequential)
Black-box aware — if remaining missions are marked ⚠️ UQ-n, the open questions from unresolved-questions.md are surfaced once at resume (answer now, or keep shipping the placeholder); answering one closes the entry and drops the marker

Examples

/resume-task
# Finds the most recent incomplete task
# Reviews progress and continues with next mission
# Maintains all previous context and technical constraints

Alternative Usage

You can also use the traditional AB Method master controller:

/ab-master resume-task

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.

2d ago First seen · 41 lines · 0 tokens per session scan A f7f862e54d1d

Subscribe to this mod's changes

resume-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 414 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.

Project management

template

Manage issue templates for streamlined issue creation.

gastownhall/beads · 0 tokens

speckit.auto

Automatically execute the four core phases of the Spec-Driven Development (SDD) pipeline: specify → plan → tasks → implement, in strict sequential order.

VisActor/VChart · 31 tokens

daily-priorities

Query DIGI Jira via the Atlassian MCP to build a prioritized daily work plan. The report has two parts: suggested priorities (the recommendation) and full context (everything you need to evaluate whether the suggestions are right and what else is on the docket).

DIGI-UW/OpenELIS-Global-2 · 0 tokens

resume-task