Skip to content
Back to skills

Context

ASecurity

Find the Architecture Decision Records most relevant to a task before implementation. Read-only and deterministic.

  • 10 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 6, 2026
ai-agentsgogit

Works with

  • cli
  • mcp

Security analysis

A100/100

Scanned October 6, 2026

npx -y skills add rvdbreemen/adr-kit --skill context --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Context?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Context
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rvdbreemen-context-adr-kit/badge)](https://www.skillsdirectory.com/skills/rvdbreemen-context-adr-kit)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: context
description: Find the Architecture Decision Records most relevant to a task before implementation. Read-only and deterministic.
license: MIT
---

<!-- Generated by scripts/build-client-adapters.py from clients/workflows.json; schema v1; client github-copilot-cli. -->
# ADR context

Select `adr-kit:context` from `/skills`, or ask Copilot to use the `context` ADR Kit skill.
Resolve `<plugin-root>` from this installed skill. Use only bundled,
local ADR Kit tools and follow this canonical workflow:

1. Take a short task topic and call the `adr-kit.adr_context` MCP tool with the absolute project root and limit 5; include known paths, components, symbols, topics, lifecycle, or authority filters.
2. Treat governing Accepted and advisory Proposed records separately, summarize explainable matches with source paths, and open only returned source ADRs before stating a binding constraint.
3. Never invent a constraint when results are empty; report index fallback or strict-index failure explicitly.

Do not contact another model or mutate user-owned instructions.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.