What is ai-first-sdlc-practices CLAUDE.md?

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

Checking project status, following its development rules, working on listed epics, and using the repository’s own development practices.

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.

How SteveGJones/ai-first-sdlc-practices configures Claude Code

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.

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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03037	$0.03037
Opus 5.5	$0.01215	$0.01215
Sonnet 5.5	$0.00607	$0.00607
Haiku 4.5	$0.00304	$0.00304

Measured 2mo ago against content hash 2b9349ad2b62, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

2mo 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 (42 stars, last pushed 1mo ago), licensed MIT. It adds 3,037 tokens to every session, about $0.0121 per session on Opus 5.5. 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.

ai-first-sdlc-practices CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-first-sdlc-practices CLAUDE.mdSteveGJones/ai-first-sdlc-practices	Instructions file	42	1mo ago	MIT	A	3,037	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

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