resume

A sprint-resumption command that detects where an interrupted or paused development sprint stopped and continues from that state.

In plain words
What is it for?
It checks the planning files, task statuses, working tree, and base branch, then handles interrupted runs, merge recovery, or forgotten sprint state.
Why use it?
It helps recover unfinished work after a crash, stopped worker, manual fix, or long gap without restarting the sprint.

Command

Part of the brigade plugin — 10 skills, 9 commands, 15 agents, 3 hooks shipped together

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/ushibo/brigade/resume
Clone the repo
git clone --depth 1 https://github.com/ushibo/brigade

Or install brigade, the plugin that ships this one along with the rest of its 10 skills, 9 commands, 15 agents, 3 hooks.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,469 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 $0.00023 $0.01469
Opus 5 $0.00012 $0.00734
Sonnet 5 $0.00005 $0.00294
Haiku 4.5 $0.00002 $0.00147

Measured 2d ago against content hash 55d914a96b42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

resume 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.

commands/resume.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are resuming a sprint that was interrupted. Auto-detect the state and continue from the right place. This command covers three scenarios:

  1. Interrupted run/brigade:run was stopped mid-wave (session crashed, user pressed ctrl+c, or workers hung). Pick up where it stopped.
  2. Manual merge recovery — a wave halted on review findings, user fixed them manually, now wants to merge outstanding branches and continue.
  3. Forgotten state — user came back after days/weeks and doesn't remember what's done.

Do not delegate orchestration to manager-agent — subagents can't spawn further subagents. This command runs at the top level.

Preflight

  1. Verify .planning/tasks/ROLES.md exists. If missing, stop and tell the user to run /brigade:init.
  2. Verify the working tree is clean (git status). If dirty, ask the user to commit or stash and stop.
  3. Confirm you are on main or master. If not, ask the user to check out the base branch and stop.

Step 1 — Detect current state

Read these inputs, in order:

  1. Current sprint: list .planning/tasks/sprint-*/, pick highest-numbered. Read _README.md.
  2. Task statuses: scan every S{N}.{M}-*.md spec file for status: field. Count done / in-progress / todo / blocked.
  3. Git branches: git branch --list 'feat/*' --no-merged main. These are outstanding branches that never got merged.
  4. Commits on main not yet recorded: git log --oneline main ^{base} filtered by feat: s{N}.{M} patterns. Find tasks whose commits are already on main but whose spec still says status: todo.
  5. Review reports: ls .planning/tasks/sprint-{N}/reviews/ — which waves have review reports, what were the verdicts.

Step 2 — Classify the situation

Based on inputs, pick ONE of these scenarios and proceed accordingly.

Scenario A: Status drift only

Some tasks have commits on main (feat: s{N}.{M} in log) but their spec still says status: todo.

Action:

  • For each drifted task, update its spec frontmatter → status: done.
  • Mark completed in sprint _README.md.
  • Commit: chore: sync sprint statuses.
  • Re-run state detection. May unlock Scenario B/C/D.

Read the full file on GitHub · 127 lines

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 · 127 lines · 23 tokens per session scan A 55d914a96b42

Subscribe to this mod's changes

resume is a command published in the GitHub repository ushibo/brigade (1 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,469 once invoked, about $0.0001 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 2026-08-31.