conductor

A phase-based workflow for taking a software idea from context gathering and technical design through implementation and deployment. It uses separate work tracks for areas such as backend, frontend, and infrastructure.

In plain words
What is it for?
Use it to define a feature’s scope and technical specification, plan database and API changes, split backend and frontend work, coordinate infrastructure tasks, and organize tests and milestones.
Why use it?
It gives larger projects a clear order of work and checkpoints. It also makes dependencies, assumptions, scope, and parallel work visible before implementation starts.

Command for Claude Code

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/liortesta/clawdagent/conductor
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

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 666 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 $0.00000 $0.00666
Opus 5 $0.00000 $0.00333
Sonnet 5 $0.00000 $0.00133
Haiku 4.5 $0.00000 $0.00067

Measured 3d ago against content hash 3ae76c67a44b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conductor 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 3d 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/conductor.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conductor Workflow — Structured Development Flow

A structured, phase-based development workflow from product vision to deployed feature. Like a symphony conductor — each instrument plays at the right time.

Phases:

Phase 1: CONTEXT (Understanding)

  • Read ALL relevant code, docs, and requirements
  • Identify existing patterns, utilities, and components to reuse
  • Map the dependency graph of affected modules
  • List unknowns and assumptions
  • Output: Context Document

Phase 2: SPEC & PLAN (Architecture)

Use CTO + Architect agents:

  • Define the feature scope (what's in / what's out)
  • Write technical specification:
    • Data model changes
    • API contract (endpoints, request/response)
    • UI components needed
    • Integration points
  • Break into development tracks:
    Track A: Backend (API + DB)
    Track B: Frontend (UI + State)
    Track C: Infrastructure (CI/CD + Config)
    
  • Define milestones and checkpoints
  • Output: Technical Spec + Task Board

Phase 3: IMPLEMENT (Track-Based)

Execute tracks in parallel where possible:

  • Track A: Backend

    1. DB migrations / schema changes
    2. Data access layer
    3. Business logic
    4. API endpoints
    5. Backend tests
  • Track B: Frontend

    1. Component structure
    2. State management
    3. API integration
    4. UI polish
    5. Frontend tests
  • Track C: Infrastructure

    1. Environment config
    2. CI/CD updates
    3. Monitoring/logging
    4. Documentation

Each track has its own QA checkpoint.

Phase 4: INTEGRATE (Merge & Test)

  • Merge all tracks
  • Run integration tests
  • Run E2E tests
  • Visual verification (/visual-verify)
  • Performance check

Phase 5: VALIDATE (Quality Gates)

  • Run /ship to check all quality gates
  • Security audit on complete feature
  • Code review with fresh eyes
  • Documentation is complete

Phase 6: DELIVER

  • Create PR with comprehensive description
  • Link to related issues
  • Tag reviewers
  • Run /wrap-up to update project memory

Output Format:

## Conductor Report — [Feature Name]

### Phase Status
| Phase | Status | Duration |
|-------|--------|----------|
| Context | DONE | ~X min |
| Spec & Plan | DONE | ~X min |
| Track A: Backend | DONE | ~X min |
| Track B: Frontend | DONE | ~X min |
| Track C: Infra | DONE | ~X min |
| Integration | DONE | ~X min |
| Validation | DONE | ~X min |

### Deliverables
- [X] Technical spec
- [X] Implementation (Y files changed)
- [X] Tests (X unit, Y integration, Z E2E)
- [X] Documentation updated
- [X] PR created: #XXX

Read the full file on GitHub · 103 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. 3d ago First seen · 103 lines · 0 tokens per session scan A 3ae76c67a44b

Subscribe to this mod's changes

conductor is a command published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 666 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.