Skip to content
Back to skills

Adr Context

ASecurity

Load relevant ADRs from docs/adr/ into context. Read-only

  • 5 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added May 27, 2026
developmentbashdatabase

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add qGolem/orc --skill adr-context --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Adr Context?

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

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

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
---
description: Load relevant ADRs from docs/adr/ into context. Read-only
user-invocable: true
context: fork
allowed-tools: Read, Glob, Bash
---

# ADR Context Loader

Load relevant architectural decisions from `docs/adr/` before implementing or verifying tasks.

## Process

1. **List all ADRs** — `Glob docs/adr/**/*.md`
2. **Extract metadata** — Read title (`# ADR-XXX: ...`) and status line from each file
3. **Filter by topic** — Identify ADRs relevant to the caller's task topic (passed as `$ARGUMENTS`)
4. **Load relevant ADRs** — Read full content of matching ADRs
5. **Output summary** — Report which ADRs apply, their decisions, and constraints to respect

## Implementation Steps

### Step 1: Discover all ADRs
```bash
Glob pattern: docs/adr/**/*.md
```

### Step 2: Read metadata
For each ADR file:
- Read the first line containing `# ADR-XXX:` to extract title
- Read the `## Status` section to determine status (Accepted, Rejected, Superseded, etc.)

### Step 3: Filter by relevance
Given the task topic from `$ARGUMENTS`, identify ADRs that match by:
- Title keywords (e.g., "auth" matches "Authentication system architecture")
- Filename patterns (e.g., `ADR-001-*.md`)
- Status (only include Accepted or superseded-but-still-relevant ones)

### Step 4: Load and return content
For each relevant ADR:
- Read the full file
- Include in output summary

### Step 5: Output summary format
```
## Relevant ADRs for [task topic]

### ADR-XXX: [Title]
- **Status**: [Accepted/Superseded]
- **Key Decision**: [one-liner]
- **Constraints to respect**:
  - Constraint 1
  - Constraint 2
- **Full decision context**: [excerpt or link]

---

### Constraints Summary
- [List all constraints from all ADRs]
```

## Example

If task topic is "auth", and docs/adr/ contains:
- `ADR-001-authentication-strategy.md` → MATCH
- `ADR-002-database-schema.md` → no match
- `ADR-003-oauth-provider-selection.md` → MATCH

Output would include ADR-001 and ADR-003 with their decisions and constraints.

## Output to Caller

Return the summary to the caller's context so they can see:
- Which ADRs apply to their task
- What architectural decisions have been made
- What constraints must be respected during implementation/verification

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.