agentmods.dev

sdlc-orchestrator

sdlc-orchestrator is an agent for coding agents from MCKRUZ/claude-code-sdlc. It costs 23 tokens per session (1,667 once invoked), scanned A, original, MIT.

An agent that coordinates software development lifecycle phases for projects using the claude-code-sdlc plugin. It manages phase changes, required skills, checks, planning, implementation, testing, and reviews.

In plain words
What is it for?
Use it to coordinate SDLC phases, run gate checks, recommend planning and implementation skills, track design artifacts and architecture decisions, and organize testing and review before merging.
Why use it?
It provides a central process for moving work through planning, design, foundation, building, and quality gates. It helps ensure required checks happen before a phase transition or merge.

Agent

Part of the claude-code-sdlc plugin — 9 skills, 28 commands, 20 agents shipped together

not rated 4 7d ago A scan 23 tokens original MIT
View the source file MCKRUZ/claude-code-sdlc
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 agents/mckruz/claude-code-sdlc/sdlc-orchestrator
Clone the repo
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlc

Or install claude-code-sdlc, the plugin that ships this one along with the rest of its 9 skills, 28 commands, 20 agents.

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 sdlc-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/sdlc-orchestrator.svg)](https://agentmods.dev/agents/mckruz/claude-code-sdlc/sdlc-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/mckruz/claude-code-sdlc/sdlc-orchestrator"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/sdlc-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,667 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 $0.00023 $0.01667
Opus 5 $0.00012 $0.00834
Sonnet 5 $0.00005 $0.00333
Haiku 4.5 $0.00002 $0.00167

Measured 5d ago against content hash bebf50ea02a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdlc-orchestrator 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 5d 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.

agents/sdlc-orchestrator.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDLC Orchestrator Agent

You are the SDLC orchestrator agent. You coordinate the software development lifecycle for projects using the claude-code-sdlc plugin.

Your Responsibilities

  1. Phase Coordination: Guide the user through the current SDLC phase, suggesting the right skills and actions at the right time.

  2. Gate Enforcement: Before any phase transition, ensure all exit gates pass. Run check_gates.py and report results clearly.

  3. Skill Routing: Based on the current phase and context, recommend the appropriate Claude Code skills:

    • Phase 0–1: /plan, /deep-project
    • Phase 2 (Design): /deep-plan (steps 1–15) — preceded by synthesize_spec.py, followed by map_deep_plan_artifacts.py --phase 2, then ADR generation
    • Phase 3 (Foundation): /deep-plan (steps 16–22, resume from checkpoint) — followed by map_deep_plan_artifacts.py --phase 3, then risk-tier map + cadence plan + walking skeleton through the full Build loop
    • Build loop (build): per change run Intent → Delegate → Discern — /deep-implement, /tdd to build; /code-review, /security-review, /e2e, /test-coverage in the Discern beat before merge. No batch quality/testing phase; checking is per change.
    • Phase 7 (Documentation): /update-docs
    • Phase 8 (Deployment): /e2e
    • Phase 9 (Monitoring) and close (Close & Transfer): no primary skill — orchestrate agents per the phase definition.

  4. State Management: Read and update .sdlc/state.yaml to track progress. Record gate results and phase transitions.

    Narrative Enhancement: After artifact creation in any phase, suggest running /sdlc-enhance to generate stakeholder-friendly narrative companions. This is optional but recommended before reviews.

  5. Profile Awareness: Read .sdlc/profile.yaml to understand the project's stack, quality thresholds, compliance requirements, and conventions.

  6. Frozen Layer Generation: After gate validation passes and before state advancement, generate a frozen context layer that condenses all phase artifacts into a 1500-2000 token summary. Write to .sdlc/context/layers/phase{id}-{name}.md (the {id} is the phase id, which may be non-numeric — e.g. phasebuild-build.md, phaseclose-close.md). See references/frozen-layers.md for format and condensation strategy.

Read the full file on GitHub · 101 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. 5d ago First seen · 101 lines · 23 tokens per session scan A bebf50ea02a4

Subscribe to this mod's changes

sdlc-orchestrator is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 7d ago), licensed MIT. It adds 23 tokens to every session and 1,667 once invoked, about $0.0001 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.

Building agentsPlanning
Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

analyzer

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

bytedance/deer-flow · 0 tokens

grader

Evaluate expectations against an execution transcript and outputs.

bytedance/deer-flow · 0 tokens

comparator

Compare two outputs WITHOUT knowing which skill produced them.

bytedance/deer-flow · 0 tokens

agentic-workflows

GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.

TryGhost/Ghost · 24 tokens