next-step

next-step is a command for Claude Code from KirKruglov/claude-project-manager. It costs 9 tokens per session (660 once invoked), scanned A, original, MIT.

A project-orchestration command that determines the next available work item from the project's current state. It checks artifact statuses, dependencies, phase rules, and required input files.

In plain words
What is it for?
Use it to inspect approved and unstarted artifacts, verify their dependencies, and recommend the next action. It is intended for projects that track work in a project-state file and an orchestration map.
Why use it?
It removes guesswork about what should happen next in a multi-step project. It also identifies work that is blocked by incomplete prerequisites or missing data.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the project-manager plugin — 21 skills, 8 commands, 3 MCP servers shipped together

Good fit Use it to inspect approved and unstarted artifacts, verify their dependencies, and recommend the next action. It is intended for projects that track work in a project-state file and an orchestration map.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kirkruglov/claude-project-manager/next-step
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.

Clone the repo
git clone --depth 1 https://github.com/KirKruglov/claude-project-manager

Made for: Claude Code.

Or install project-manager, the plugin that ships this one along with the rest of its 21 skills, 8 commands, 3 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for next-step

README.md
[![agentmods](https://agentmods.dev/badge/commands/kirkruglov/claude-project-manager/next-step.svg)](https://agentmods.dev/commands/kirkruglov/claude-project-manager/next-step)
Your own site
<a href="https://agentmods.dev/commands/kirkruglov/claude-project-manager/next-step"><img src="https://agentmods.dev/badge/commands/kirkruglov/claude-project-manager/next-step.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 660 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00009 $0.00660
Opus 5 $0.00005 $0.00330
Sonnet 5 $0.00002 $0.00132
Haiku 4.5 $0.00001 $0.00066

Measured 7d ago against content hash 7863387688cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

next-step 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 7d 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/next-step.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.

Next Step

Analyze project state and orchestration rules to recommend the immediate next action.

Process

1. Read Project State

Read project-state.md to get:

  • Current phase
  • Status of all 34 artifacts
  • Which artifacts are "approved", "in_progress", "not started"

2. Read Orchestration Map

Read references/orchestration-map.md to understand:

  • Artifact dependencies (which artifacts must complete before others can start)
  • Skill-to-artifact mapping (which skills produce which artifacts)
  • Phase progression rules
  • Blocking conditions for phase transitions

3. Identify Available Next Steps

For each artifact with status "approved":

  • Check if all dependent prerequisites have status "completed"
  • If yes, that artifact is "ready to execute"

For each artifact with status "not started":

  • Check if all dependencies have status "approved" or "completed"
  • If yes, and no other blocker exists, that artifact is "available to start"

4. Validate Input Data

For each available artifact:

  • Check if required input data exists in input/ folder
  • Verify data completeness (no critical missing fields)
  • If data is missing, flag as "blocked pending input"

5. Present Recommendations

Display 1-3 recommended next steps in priority order:

# Recommended Next Steps

## Priority 1: [Artifact Name] (ID: #X)
**Status**: [Ready to execute / Available to start / Blocked]
**Skill**: [Skill name from orchestration map]
**Dependencies**: [All satisfied / Missing Y, Z]
**Rationale**: [Why this is the next logical step]

**Action**: 
- If ready: "Run skill [skill-name] now"
- If blocked: "Waiting for [artifact] or [input file] — see requirements below"

---

## Priority 2: [Artifact Name] (ID: #Y)
[Same format]

---

## Priority 3: [Artifact Name] (ID: #Z)
[Same format]

---

## Blocking Issues (if any)
- [Issue 1]: Cannot proceed to Phase N without artifact #M
- [Issue 2]: Missing input: [file name] required for artifact #X

6. Offer Confirmation

If user confirms the recommended step:

  • Extract skill name
  • Trigger skill with appropriate parameters
  • Pass artifact_id, phase, project_path to the skill
  • Update project-state.md upon skill completion

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. 7d ago First seen · 103 lines · 9 tokens per session scan A 7863387688cf

Subscribe to this mod's changes

next-step is a command published in the GitHub repository KirKruglov/claude-project-manager (6 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 660 once invoked, about $0.0000 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.