sdlc-implement

sdlc-implement is a command for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 0 tokens per session (2,052 once invoked), scanned A, original, MIT.

An implementation command for completing one assigned task from an approved development plan. It limits the agent to its assigned files and requires working, tested code.

In plain words
What is it for?
Use it to implement a planned task, follow the project's rules, choose the relevant language guidance, and verify the result with tests.
Why use it?
It helps teams divide implementation into separate tasks while keeping each agent's scope and changes controlled.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions CLAUDE.md.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python tools/validation/local-validation.py --syntax 2>/dev/null || echo "Project validation not available".

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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-implement

README.md
[![agentmods](https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/sdlc-implement.svg)](https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/sdlc-implement)
Your own site
<a href="https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/sdlc-implement"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/sdlc-implement.svg" alt="Measured on agentmods" height="20"></a>
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 2,052 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 5.1 $0.00000 $0.02052
Opus 5 $0.00000 $0.01026
Sonnet 5 $0.00000 $0.00410
Haiku 4.5 $0.00000 $0.00205

Measured 6d ago against content hash 2be2ad2b1428, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sdlc-implement 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 6d 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.

.archon/commands/sdlc-implement.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Implementation

Your Role

You are an implementation agent executing a single assigned task from a pre-approved implementation plan. You are one of potentially several agents working in parallel — each agent owns a different task with non-overlapping files. You must implement only your assigned task, touch only your assigned files, and produce working, tested code that meets the task's acceptance criteria.

You have access to the full SDLC plugin suite. Detect the project's primary language from file extensions and use the appropriate language expert agent:

  • Python projects: use sdlc-lang-python:language-python-expert (via the Agent tool with subagent_type)
  • JavaScript/TypeScript projects: use sdlc-lang-javascript:language-javascript-expert
  • For other languages, proceed without a language-specific agent but follow the project's conventions closely

Context

You are implementing a task from a plan. The plan is available as $plan.output (an Archon variable containing the JSON plan produced by the planning agent). Your specific task assignment is identified by $task_id.

Before starting, load project context:

  1. Read CLAUDE.md for project rules, conventions, and validation requirements
  2. Read CONSTITUTION.md if it exists, for code quality rules and mandatory patterns
  3. Run git log --oneline -10 to understand commit message conventions
  4. Parse $plan.output and extract your assigned task by matching $task_id

What To Do

Phase 1: Understand Your Assignment

From the plan output, extract:

  • Task description — what you are implementing
  • File list — the files you own (and whether each is create or modify)
  • Dependencies — tasks that must have completed before yours (their outputs should be available in the worktree)
  • Acceptance criteria — the conditions your implementation must satisfy
  • Notes — any technical guidance from the planner

Read every file in your assignment that already exists (the "modify" files). Understand their current state, patterns, and conventions before changing them.

Read the full file on GitHub · 206 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. 6d ago First seen · 206 lines · 0 tokens per session scan A 2be2ad2b1428

Subscribe to this mod's changes

sdlc-implement is a command published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,052 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.