do-next-steps

A command for deciding and carrying out the next implementation work in a codebase. It examines project documentation and architecture, then organizes work around interfaces so independent parts can be developed in parallel.

In plain words
What is it for?
Use it to inspect README files, roadmaps, architecture documents, and agent instructions; identify blockers and parallel work; and create and execute an implementation plan.
Why use it?
It replaces guesswork about what to build next with a plan based on the repository's stated status, missing pieces, dependencies, and current documentation.

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/consiliency/code-index-mcp/do-next-steps
Clone the repo
git clone --depth 1 https://github.com/Consiliency/Code-Index-MCP

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 1,823 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 $0.01823
Opus 5 $0.00000 $0.00911
Sonnet 5 $0.00000 $0.00365
Haiku 4.5 $0.00000 $0.00182

Measured 2d ago against content hash a1f51c0316a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

do-next-steps 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/do-next-steps.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

do-next-steps

Execute the next implementation steps for any codebase using interface-driven parallel development to maximize agent productivity and ensure clean architecture.

METHODOLOGY: INTERFACE-DRIVEN PARALLEL DEVELOPMENT

This command analyzes any codebase's documentation structure (README.md, ROADMAP.md, architecture/ directory, AGENTS.md files) to create and execute a comprehensive implementation plan that maximizes parallelism through interface-based development.

DISCOVERY PHASE

1. Analyze Project Documentation

# Discover current project state dynamically
find . -name "README.md" -o -name "ROADMAP.md" -o -name "*.md" | head -20
find . -type d -name "architecture" -o -name "docs" -o -name "design"
find . -name "AGENTS.md" -o -name "CLAUDE.md" | sort

Extract Key Information:

  • Project purpose and scope (from README.md)
  • Implementation status and next steps (from ROADMAP.md)
  • Architecture components and gaps (from architecture/ directory)
  • Current implementation percentage (from status indicators)
  • Critical path items (blocking other work)
  • Parallel execution opportunities (independent components)

2. Identify System Architecture

# Discover architectural components
find . -name "*.puml" -o -name "*.dsl" -o -name "*architecture*"
ls -la */interfaces/ */contracts/ */api/ 2>/dev/null || echo "No existing interfaces"
find . -name "*interface*" -o -name "*contract*" -o -name "*protocol*"

Analyze Architecture Patterns:

  • Layered architecture (API, Business, Data layers)
  • Microservices (independent services)
  • Plugin/Extension systems (dynamic loading)
  • Event-driven (pub/sub patterns)
  • Modular monolith (domain boundaries)

3. Assess Implementation Gaps

# Identify implementation vs design gaps
find . -name "*stub*" -o -name "*todo*" -o -name "*placeholder*"
grep -r "NotImplementedError\|TODO\|FIXME\|XXX" --include="*.py" --include="*.js" --include="*.ts"
find . -name "*test*" | wc -l  # Test coverage indicator

Read the full file on GitHub · 272 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 · 272 lines · 0 tokens per session scan A a1f51c0316a7

Subscribe to this mod's changes

do-next-steps is a command published in the GitHub repository Consiliency/Code-Index-MCP (57 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,823 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.