ai-sdlc-framework: Skill for Claude Code

.claude/skills/SDLC-elicit/SKILL.md

SDLC-elicit is a skill for Claude Code from pangon/ai-sdlc-framework. It costs 44 tokens per session (3,782 once invoked), scanned A, original, Apache-2.0.

An interactive guide for defining and reviewing software requirements, including stakeholders, goals, user stories, assumptions, and constraints.

In plain words
What is it for?
Use it to create or modify specification documents and perform a gap analysis of existing project requirements.
Why use it?
It helps uncover missing information before technical design and coding begin, while warning about the impact of later specification changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is pangon/ai-sdlc-framework's own configuration. It tells Claude Code how to work on ai-sdlc-framework 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-sdlc-framework configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pangon/ai-sdlc-framework. 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/pangon/ai-sdlc-framework/main/.claude/skills/SDLC-elicit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pangon/ai-sdlc-framework

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-elicit

README.md
[![agentmods](https://agentmods.dev/badge/skills/pangon/ai-sdlc-framework/sdlc-elicit.svg)](https://agentmods.dev/skills/pangon/ai-sdlc-framework/sdlc-elicit)
Your own site
<a href="https://agentmods.dev/skills/pangon/ai-sdlc-framework/sdlc-elicit"><img src="https://agentmods.dev/badge/skills/pangon/ai-sdlc-framework/sdlc-elicit.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,782 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 127
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 138
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 169
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00044 $0.03782
Opus 5 $0.00022 $0.01891
Sonnet 5 $0.00009 $0.00756
Haiku 4.5 $0.00004 $0.00378

Measured 8d ago against content hash ea6ab785963f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

SDLC-elicit 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 8d 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/skills/SDLC-elicit/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions

You are running an interactive elicitation session for the Specification phase of an AI-first SDLC project. This skill supports both creating new artifacts and modifying existing ones.

Phase Validation

Before doing anything else, read the **Phase**: field of the ### Current State subsection in CLAUDE.md. Then follow the matching case below:

  1. Not initializedStop, recommend /SDLC-init, and do not proceed.

  2. Specificationproceed normally with the Setup steps below.

  3. Design or Code — the project has advanced beyond Specification. Warn that modifying Specification artifacts may impact downstream design, tasks, or deployed code. If the user confirms, proceed but flag downstream dependencies that could be affected.

Setup

  1. Read 1-spec/CLAUDE.spec.md (phase instructions and existing artifact indexes).
  2. Read 1-spec/stakeholders.md to understand existing stakeholders.
  3. Check the ## Decisions Relevant to This Phase index in 1-spec/CLAUDE.spec.md: read any decisions whose trigger conditions apply, and apply their enforcement rules throughout the elicitation session.

Artifact Traceability Chain

Specification artifacts form a traceability chain. Each level should decompose into the next:

  1. Stakeholder → Goals — every stakeholder should have at least one associated goal. A stakeholder with no goals has no defined value proposition in the project.
  2. Goal → User Stories — every goal should have at least one associated user story. Review the linked user stories against the goal's success criteria and flag coverage gaps.
  3. User Story → Requirements — every user story should have at least one associated requirement. Review the linked requirements against the story's acceptance criteria and flag obvious coverage gaps.
  4. Constraint → Requirements — constraints may also generate requirements directly (e.g., a compliance constraint produces a compliance requirement, a technology constraint produces a compatibility requirement). When a constraint implies a verifiable obligation, derive a requirement from it and link both.

Read the full file on GitHub · 176 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. 8d ago First seen · 176 lines · 44 tokens per session scan A ea6ab785963f

Subscribe to this mod's changes

SDLC-elicit is a skill published in the GitHub repository pangon/ai-sdlc-framework (126 stars, last pushed 15d ago), licensed Apache-2.0. It adds 44 tokens to every session and 3,782 once invoked, about $0.0002 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens