><(((*>

Just Keep Swimming

v2: scrum-master execution for Claude Code — parallel dev agents, review gates, and a live board. Your AI ships multi-phase plans start to finish, no matter how many sessions it takes.

Install in 10 seconds ↓

Context rot is silent and expensive

When an AI agent's context window fills up, the system compresses earlier messages and the agent keeps working on subtly wrong assumptions. On big plans the damage compounds: phases run one at a time even when they're independent, and the agent burns its own context reading source files until its early decisions turn to fog.

🔄

Repeated questions

The agent re-asks things it already resolved an hour ago, wasting time and breaking flow.

🚧

Architectural drift

Implementations silently deviate from decisions made earlier in the session when those decisions get compressed away.

💥

Regression by amnesia

The agent breaks things it just built because it forgot why they were built that way.

One agent coordinates. Many agents build.

v2 turns your session into a scrum master. It dispatches parallel dev agents with disjoint file ownership, reviews every phase before merging, ships as it goes, and keeps one live board so any session can resume from two file reads.

1

Plan

Create or import an implementation plan

2

Dispatch

Parallel dev agents, each owning its files

3

Review & merge

Adversarial gate, then ship while the next sprint runs

4

Board

Live state; any session resumes from two reads

What's in the box

Core

The live board

One BOARD.md per plan holds phase states, commit SHAs, decisions, and learnings with exact file:line references. Updated at every sync point, so a crash loses one sprint at most.

Smart

Audited against git

scripts/board-check.js verifies every merged claim, the progress count, the ship SHA, and the door state against git itself. A board that lies blocks dispatch until it's fixed.

Flexible

Three lanes

Lite for half-day jobs (one file, one gate), solo for small serial plans, scrum for parallel agent orchestration. Route by flag or by scope.

Precise

The tier doctrine

The strongest model orchestrates, one tier down develops, rote lanes go two tiers down, and the riskiest review gates use the orchestrator's own model. Every model earns its cost.

Tracked

Review gates

Every phase is adversarially reviewed before its merge. Fixes go back to the same warm agent; two failed rounds parks the phase for a human instead of looping.

Light

One plugin, zero config

Install with a single command. No daemons, no setup wizards. Plans and boards are markdown in your repo, plus one small audit script.

Autonomous

Night build pipeline

End-of-day sweep: parallel reviewers over the day's commits, confident fixes applied, tests, deploy through your release path, summary for the morning. Fully unattended.

Adaptive

Fresh sessions, not compaction

Sessions run in shifts that end at clean board boundaries. The next session resumes with full acuity instead of a compacted one guessing at what it forgot.

Instant

Plan from conversation

Already discussing architecture? Use --from-context to distill the conversation into a structured plan. Add --now to skip confirmations.

Durable

Post-delivery maintenance

Completed plans stay useful. Bug reports get structured debugging with maintenance logs, not ad-hoc guessing.

What the board actually looks like

Live state, not an archaeology dig. This is everything a fresh session reads to take over, and the checker verifies it against git before any work is dispatched.

  BOARD.md
# Board — API Migration **Updated**: 2026-03-13 22:41 · **Door**: wt-api-migration (open) **Progress**: 4/6 phases merged · **Shipped**: abc1234 ## Status | 3. Auth middleware | merged | Dev-3 | middleware/auth.js | e19af02 | | 4. Session store | merged | Dev-4 | services/session.js | b7d2c11 | | 5. Rate limiting | review | Dev-5 | services/rateLimiter.js | — | | 6. Legacy cutover | todo | — | routes/*.js | — | ## Decisions (settled) - merge: FF to main · deploy: npm run deploy · checks: npm test ## Learnings (cumulative) - Redis keys follow `user:{id}:session` (TTL 30min) - Rate limiter must exempt /health — `services/rateLimiter.js:88` ## Blockers - P6 waits on the DNS cutover window (user decision) $ node scripts/board-check.js api-migration BOARD OK — 5 checks, 6 phases, 0 warnings

Your workflow, your way

Autonomous Default

Runs sprint after sprint and keeps the board current. Invoke it bare to resume the most recent active plan; go status just reports.

/justkeepswimming:go my-feature

Interactive --interactive

Pauses at sprint boundaries. Review results, adjust the plan, decide when to continue.

/justkeepswimming:go my-feature --interactive

Lightweight by design

Just Keep Swimming Heavy workflow systems
Installation 1 plugin command 30+ files
State tracking One live board, audited against git STATE.md, ROADMAP.md, CONTEXT.md, etc.
Concepts to learn Plan, Board, Sprint, Merge window Projects, Milestones, Phases, Waves, Audits
Parallelism File-ownership lanes, review gates, one git owner Unmanaged, or none
Setup time 10 seconds Plugin install + configuration
Dependencies None required Plugin ecosystem
Commands 2 commands + a status call 10+ specialized agents

Agents that think, not just execute

Most AI agents fail the same way: they pattern-match to common fixes and try them one by one. Just Keep Swimming ships with six problem-solving principles injected into every session — changing how the agent approaches problems.

1

Diagnose before you prescribe

Gather facts before forming hypotheses. Every minute understanding the problem saves ten minutes of wrong-direction fixes.

Anti-pattern: "This looks like X, so let me try the usual fix."
Correct: "Let me verify what's actually happening first."
2

Trace the full chain

List every condition required for success and verify each one. The broken condition is always the one nobody checks because it's "too basic."

3

Check what's actually there

Run diagnostics with an open mind. Read the actual output — don't skim for confirmation of what you already believe.

4

Know the silent failures

Systems fail without useful errors all the time. They fall back, return generic messages, or silently skip the broken path. Find the quiet one.

5

Minimum effective intervention

Fix the root cause and only the root cause. The best fix is the smallest change. If you changed more than needed, you didn't understand the problem well enough.

6

Resist "the usual fix"

If the user has tried everything, the obvious solutions are exhausted. The answer lives in the layer nobody checked yet. Don't re-run the playbook.

"Don't be a solution-guesser. Be a condition-verifier."

Every condition required for success must be verified. The one you skip is the one that's broken. v2 adds the Orchestrator's Corollary for scrum-lane work: delegate the noise, keep the signal. The protocol is customizable. Add your team's debugging lessons to THINKING.md and every future session inherits them.

Up and running in 10 seconds

Install as a plugin or copy two files. No dependencies.

1 Add the marketplace

/plugin marketplace add cyber-qais/justkeepswimming

2 Install the plugin

/plugin install justkeepswimming

3 Use it

Open any Claude Code session and run:

/justkeepswimming:go my-feature

Alternative: Manual install

mkdir -p ~/.claude/commands/justkeepswimming
cp commands/justkeepswimming/*.md ~/.claude/commands/justkeepswimming/

Alternative: npm

npm install justkeepswimming
Works with any Claude Code project. Optionally pairs with the superpowers plugin for auto-generated plans.
Available on GitHub · npm