AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Context

skill-rvdbreemen-adr-kit-context · by rvdbreemen

Loads the Architecture Decision Records most relevant to a task before you implement it, so existing decisions are honored without burning context on the whole ADR set. Give it a topic (e.g. "mqtt discovery", "heap allocation", "caching") and it returns the 3-5 most relevant Accepted ADRs as readable context — title, one-line decision, file path, and relevance score. Read-only and safe to call fr…

↗ Repository
— No reviews yet
0 installs
33 views
0.0% view→install

Install

$ agentstack add skill-rvdbreemen-adr-kit-context

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-rvdbreemen-adr-kit-context)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Context? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

adr-kit context

You are running /adr-kit:context. Purpose: surface the ADRs that constrain the task at hand before writing code, so you implement within existing decisions instead of rediscovering or contradicting them. This is read-only — it never edits ADRs or code, so it is safe to call from parallel subagents.

Procedure

  1. Take the topic from the argument. If none was given, ask the user for a short

topic or task description (one phrase is enough).

  1. Run the bundled deterministic ranker from the project root. Request JSON so

you get the relevance signals, and keep the default limit of 5:

``bash python /bin/adr-context --format json --limit 5 "" ``

  • Use --adr-dir if the project keeps ADRs somewhere other than

docs/adr/.

  • Use --min-score to tighten or loosen the relevance cutoff

(default 0.1).

  1. If the result is an empty list ([]): tell the user plainly —

"No ADRs match ''; all existing ADRs may apply, or none constrain this work." Do not invent relevance. Stop here.

  1. Otherwise, for each returned ADR, Read the file and present it as

readable context, not just a filename:

  • ADR-NNN — (relevance: ``)
  • one-line summary of its ## Decision (paraphrase the decision, don't dump

the whole section)

  • file path, so the user can open the full record

Order by relevance (highest first), most relevant ADR last in your message so it stays closest to the work that follows.

  1. Briefly state the net constraint: in one or two sentences, what these

decisions require or forbid for the task. Then proceed with (or hand back to) the implementation.

Boundaries

  • Read-only. Never modify ADRs, code, or status during a context load.
  • Report relevance honestly — a low score means "weakly related", not "must

comply". Do not inflate scores to seem thorough.

  • The ranker is a heuristic. If the user mentions a decision you do not see in

the results, widen with a different topic or lower --min-score rather than assuming no ADR exists.

  • Loading context is not approval to violate a decision. If the task conflicts

with an Accepted ADR, surface the conflict and use /adr-kit:judge or /adr-kit:adr to resolve it.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Developer Tools