ai-sdlc-framework CLAUDE.md

ai-sdlc-framework CLAUDE.md is an instructions file for coding agents from pangon/ai-sdlc-framework. It costs 3,473 tokens per session, scanned A, original, Apache-2.0.

Instructions for an AI-first software development framework, where project decisions, requirements and tasks are stored alongside the code. The project is currently a fresh, uninitialised framework.

In plain words
What is it for?
Use them when initialising the project, documenting requirements or moving through its specification and development phases.
Why use it?
They keep project communication in the framework's shared records and prevent important decisions from being hidden in private assistant memory.

Instructions file

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 instructions/pangon/ai-sdlc-framework/claude-md
Clone the repo
git clone --depth 1 https://github.com/pangon/ai-sdlc-framework

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-sdlc-framework CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pangon/ai-sdlc-framework/claude-md.svg)](https://agentmods.dev/instructions/pangon/ai-sdlc-framework/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pangon/ai-sdlc-framework/claude-md"><img src="https://agentmods.dev/badge/instructions/pangon/ai-sdlc-framework/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,473 This file is loaded in full into every session.
When invoked 3,473 The same file — it is already loaded in full.
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 $0.03473 $0.03473
Opus 5 $0.01736 $0.01736
Sonnet 5 $0.00695 $0.00695
Haiku 4.5 $0.00347 $0.00347

Measured 5d ago against content hash f40ab39d7ef6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-sdlc-framework 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 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.

CLAUDE.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Language Policy

All AI outputs must be in English, regardless of the language used in user prompts. This applies to code, comments, documentation, configuration files, commit messages, and response text.

Memory Policy

Do not use Claude memory files to store project information. All project knowledge — domain context, team structure, constraints, decisions, and any other relevant information — must be captured exclusively through the SDLC artifact system (stakeholders, constraints, assumptions, goals, requirements, decisions, etc.). This ensures all knowledge is structured, traceable, and available to every team member working on the project.


Project Overview

This repository uses a structured, AI-first development lifecycle. All project knowledge — specification, design, decisions, tasks — lives alongside the source code.

Current State

Phase: Not initialized

Summary: Pristine framework, not yet initialized. The repository contains the AI SDLC Framework (phase directories, templates, automation skills), ready to be populated starting from the Specification phase after initialization (/SDLC-init).


Current State Protocol

The ### Current State subsection above is the machine-readable project status shared by all skills. Its structure:

  • **Phase**: — mandatory first line. One of: Not initialized, Specification, Design, Code. Every skill validates its applicability against this field before acting.
  • **Summary**: — mandatory. One or two sentences of free text describing where the project stands.
  • Standardized status lines — each optional, appearing at most once, added when its activity first occurs, then updated in place; never removed:
Line Format Primary maintainer
**Spec artifacts**: artifact types worked on so far SDLC-elicit
**Gap analysis**: active or passed form — see Assessment lines below SDLC-elicit
**Design documents**: drafting status per document SDLC-design
**Completeness assessment**: active or passed form — see Assessment lines below SDLC-design
**Components**: comma-separated component names SDLC-decompose
**Implementation plan**: created YYYY-MM-DD — N phases, M tasks SDLC-implementation-plan
**Task progress**: D/M tasks done — currently in Phase N (name) SDLC-execute-task

Read the full file on GitHub · 187 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 · 187 lines · 3,473 tokens per session scan A f40ab39d7ef6

Subscribe to this mod's changes

ai-sdlc-framework CLAUDE.md is an instructions file published in the GitHub repository pangon/ai-sdlc-framework (125 stars, last pushed 12d ago), licensed Apache-2.0. It adds 3,473 tokens to every session, about $0.0174 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.