ai-first-sdlc-practices: Instructions file for Claude Code

CLAUDE.md

ai-first-sdlc-practices CLAUDE.md is an instructions file for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 3,037 tokens per session, scanned A, original, MIT.

Project instructions for an AI-first software-development framework, including its rules, current work, completed work, and expected workflow.

In plain words
What is it for?
Checking project status, following its development rules, working on listed epics, and using the repository’s own development practices.
Why use it?
They give a coding agent the project’s working context and constraints, helping it avoid treating finished work as pending or changing the repository in the wrong way.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions subagents; mentions Codex.

This is SteveGJones/ai-first-sdlc-practices's own configuration. It tells Claude Code how to work on ai-first-sdlc-practices itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-first-sdlc-practices configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SteveGJones/ai-first-sdlc-practices. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SteveGJones/ai-first-sdlc-practices/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices

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 ai-first-sdlc-practices CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stevegjones/ai-first-sdlc-practices/claude-md/github.svg)](https://agentmods.dev/instructions/stevegjones/ai-first-sdlc-practices/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/stevegjones/ai-first-sdlc-practices/claude-md"><img src="https://agentmods.dev/badge/instructions/stevegjones/ai-first-sdlc-practices/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-first-sdlc-practices CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/stevegjones/ai-first-sdlc-practices/claude-md"><img src="https://agentmods.dev/badge/instructions/stevegjones/ai-first-sdlc-practices/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,037 This file is loaded in full into every session.
When invoked 3,037 The same file — it is already loaded in full.
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 $0.03037 $0.03037
Opus 5 $0.01519 $0.01519
Sonnet 5 $0.00607 $0.00607
Haiku 4.5 $0.00304 $0.00304

Measured 9d ago against content hash 2b9349ad2b62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-first-sdlc-practices CLAUDE.md 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 9d 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.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AI Development Instructions

AI-First SDLC Practices framework for AI development (v1.8.0). Rules: CONSTITUTION.md. Full instructions: CLAUDE-CORE.md.

Active Work

Nothing is currently in flight. The items below are open but unstarted or partially landed — verify state before assuming.

  • EPIC #197 — sdlc-knowledge-base v0.3.0 operator experience + scale. Phases A and B are on main (PR #198 merged; kb-layers, kb-stats, kb-prepare-batch, kb-ingest-batch all present). Phase C is what remains: #163 confidence metadata, #165 lint auto-fix. Spec: docs/superpowers/specs/2026-05-03-kb-v030-phase-b-design.md. Note the old branch feature/kb-v030-operator-experience still exists on the remote — check whether it is stale before reusing it rather than branching from main.
  • EPIC #97 — Multi-Option Commissioned SDLC. Sub-features for Single-team (#99) / Solo (#100) bundles still pending. Migration skill (#101) and docs (#102) also pending.

Recently completed — context, not work

  • #237 — poker-capstone / sdlc-model-council assessment. CLOSED and merged (PR #238 798447d, research note PR #239 323732f). Shipped the P1-P10 capability ladder, a local-model agentic harness, and an assessment-first reframing of the plugin. Outcome: the local-model seat is closed — both auditioned 4-bit models fail P1, the easiest phase. Two things to carry forward:
    • research/poker-capstone/runs/ and broken-variants/ are exempted from four validators (flake8, CodeQL, technical-debt, logging). That is deliberate: they hold verbatim model output, some defective on purpose as a recorded result, and must stay byte-identical to be re-verifiable. Do not "fix" lint findings in there. Two of those validators auto-detect framework-vs-application context by file ratio, so a large new corpus can silently flip the whole repo onto strict rules.
    • Open follow-ups are listed in memory poker-capstone-p11-status — the main integration gap is folding ladder results into the roster card format (plugins/sdlc-model-council/scripts/council/roster.py).

Read the full file on GitHub · 160 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. 9d ago First seen · 160 lines · 3,037 tokens per session scan A 2b9349ad2b62

Subscribe to this mod's changes

ai-first-sdlc-practices CLAUDE.md is an instructions file published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 3,037 tokens to every session, about $0.0152 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens