Install
$ agentstack add skill-qgolem-orc-adr-context ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
ADR Context Loader
Load relevant architectural decisions from docs/adr/ before implementing or verifying tasks.
Process
- List all ADRs —
Glob docs/adr/**/*.md - Extract metadata — Read title (
# ADR-XXX: ...) and status line from each file - Filter by topic — Identify ADRs relevant to the caller's task topic (passed as
$ARGUMENTS) - Load relevant ADRs — Read full content of matching ADRs
- Output summary — Report which ADRs apply, their decisions, and constraints to respect
Implementation Steps
Step 1: Discover all ADRs
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
## Statussection to determine status (Accepted, Rejected, Superseded, etc.)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ADR-001-*.md) - Status (only include Accepted or superseded-but-still-relevant ones)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- **Status**: [Accepted/Superseded]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→ MATCHADR-002-database-schema.md→ no matchADR-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
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: qGolem
- Source: qGolem/orc
- License: MIT
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.