discipline
AI coding agent workflow harness
Ship clean code. Not AI bloat.
The right level of engineering discipline for every task. Reuse what exists, match the project, and go playoff mode only when the stakes demand it.
discipline
AI writes fast.
It should also know
when to stop.
+ src/components/LogoutButton.tsx
+ src/styles/logout-button.css
+ src/theme/logout-tokens.ts
+ src/services/auth-controller.ts
+ src/hooks/useLogoutFlow.ts
<Button variant="default"
onClick={handleLogout}>
Logout
</Button>
- 01 Existing code
- 02 Standard library
- 03 Native feature
- 04 Installed dependency
- 05 Smallest new implementation
Every task
is not game seven.
Start light. Add process only when risk earns it. mancode lets the same coding agent move from daily practice to production-grade review without changing tools. Ordinary Solo stays lightweight; governed tasks retain their original gates, with review depth guided by risk and new evidence.
solo
Move fast.
Stay on system.
For everyday changes that need context, not ceremony—even with newer models that already self-review.
- Lightweight hooks
- Check the actual diff
- Independent review when needed
/manba
Reproduce.
Diagnose. Verify.
For defects that need a root cause and a real regression check.
- Reproduce the failure
- Drive real user paths
- Verify the fix in runtime
/man
Plan every
possession.
Align requirements, compare options, and approve a durable plan before choosing delivery depth.
- Guided requirement alignment
- Solo handoff with inherited gates
- Optional full nine-step governance
/manteam
Five on floor.
One memory.
For teams that need shared decisions to survive across agent sessions.
- Shared project memory
- Decision records
- Conventional commits
/manps
Find the rust
before tipoff.
For maintenance passes that surface debt without rewriting the project.
- Stale TODO detection
- Dependency checks
- Markdown + JSON reports
/man workflow
From scout report
to final buzzer.
Every planning run leaves a readable trail under
.mancode/<namespace>/workflows/<ULID>/. After approval, assign delivery to solo or continue the Man workflow. Both paths retain the approved plan, scope, review, and acceptance gates.
- 01Scout reportMap code, risks, unknowns
- 02ClarifyResolve the real requirement
- 03PlanCreate verifiable steps
- 04Plan gateSolo, full governance, plan-only, or revise
- 05ImplementHead Coach runs the play
- 06VerifyBuild, lint, test, smoke
- 07Targeted reviewEvidence-backed quality findings
- 08Risk defenseSecurity review only when risk requires it
- 09Close outResolve blockers, reverify, complete
Read the room
before writing.
mancode detects the project shape, available validation commands, existing components, CSS variables, and design signals. UI guidance only activates when the project actually has a UI.
your-project/
├── .mancode/
│ ├── shared/context/project.json
│ ├── local/cache/style-tokens.json
│ ├── local/workflows/<ULID>/
│ └── shared/team/
├── .claude/
├── .cursor/rules/
├── .agents/skills/
└── AGENTS.md
✓ context stays with the code
✓ no telemetry sent
New in 0.5.0
Choose the look.
Then make it real.
A new UI or visual redesign no longer starts from one silent default. When the direction is open, mancode asks the agent for 2–3 product-appropriate routes, the tradeoffs, and a recommendation. You choose. Then it builds one coherent system. Emoji remain valid in user-authored content, but never stand in for interface icons.
Configure the policy2–3 routes.
Distinct visual logic. Clear tradeoffs. One recommendation. No code until the direction is yours.
- 01Editorial precisionQuiet / typographic
- 02Technical theatreBold / kinetic
- 03Product clarityDense / functional
preserve
Keep the hierarchy, components, layout, and interaction patterns. Change only what the task requires.
refine
Improve type, spacing, hierarchy, states, and responsive behavior without changing the product structure.
experimental
Allow one stronger composition and purposeful motion—after confirmation, inside the existing product scope.
One playbook.
Your tools.
mancode is a workflow layer, not another coding agent. Claude Code gets the richest native integration; other tools receive durable rules, skills, or instruction files.
One task.
Another session.
mancode keeps goals, requirements, plans, validation results, and handoff notes under a stable TaskRef. A new chat or CLI session can resume that task, load bounded references, and read the required bodies by version without keeping the previous window open.
mancode context resume <TaskRef> --session <id> --client <client>Explicit identity
Every project.
One clear view.
A task board, module overview, decisions, timeline, and lessons learned share the same registered project facts. Completions, blockers, and acceptance changes update the page. Rendering and idle refresh make no model calls.
Index first. Read on demand.
Start with bounded references and read required bodies by version. A growing project does not put every document into every conversation.
Keep reasons and applicability.
Distinguish current, partially valid, and historical records. Follow sources to understand replacements and revocations.
Move work by status.
Not started, in progress, in review, and blocked columns. Plan-only work stays marked; completed tasks are collapsed.
Open locally. Preview on demand.
New projects generate HTML during initialization. Existing projects run mancode progress init. Offline files need no server.

Ready at the buzzer
Put mancode
in the rotation.
No account, dashboard, API key, or new editor. Initialize it inside the project you already use—Windows CMD, PowerShell, Git Bash, macOS, and Linux are supported.
Read the docs ↗npm install -g mancode
cd your-project
mancode init
Less ceremony for the easy work.
More discipline for the work that matters.