adr-review
Review Architecture Decision Records for staleness, superseded decisions, missing outcomes, and unlisted alternatives
Skill by hummbl-io
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hummbl-io-adr-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/adr-review
What's inside
- Skill name
adr-review- Description
- Review Architecture Decision Records for staleness, superseded decisions, missing outcomes, and unlisted alternatives
- License
- Apache-2.0
- Instructions
- 68 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
---
name: adr-review
description: Review Architecture Decision Records for staleness, superseded decisions, missing outcomes, and unlisted alternatives
version: 0.1.0
execution-mode: advisory
argument-hint: "[--scope all|ADR_ID] [--check staleness|outcomes|alternatives]"
category: backend-infra
status: candidate
---
# ADR Review
Audit Architecture Decision Records for quality, currency, and completeness. Checks whether decisions are stale (context has changed), superseded without being marked, missing outcome documentation, or lacking alternative analysis. Helps keep the decision log reliable and actionable.
## When to Use
- Periodic review of architectural decisions for staleness
- Before making a new decision in an area with existing ADRs
- When onboarding someone who needs to understand past decisions
- After a major refactor to check if ADRs still reflect reality
## Execution
1. **Locate ADRs** -- scan for decision records in:
- `docs/decisions/`, `docs/adr/`, `adr/` directories
- Ledger entries with type `DECISION`
- Decision log entries from `[decision-log]`
2. **Staleness check** (if `--check staleness` or `all`):
- Compare decision context against current codebase state
- Flag ADRs where the described problem no longer exists
- Flag ADRs where the chosen solution was never implemented
- Flag ADRs older than 12 months without review
3. **Superseded check** (all scopes):
- Find ADRs that contradict each other
- Identify decisions that were effectively reversed by later commits
- Flag ADRs not marked as superseded when a newer one exists
4. **Outcomes check** (if `--check outcomes` or `all`):
- Verify each ADR documents the actual outcome (not just the decision)
- Flag ADRs missing consequences, trade-offs, or follow-up actions
- Check if predicted risks materialized
5. **Alternatives check** (if `--check alternatives` or `all`):
- Verify each ADR lists at least 2 alternatives considered
- Flag decisions made without documented alternatives
- Check if rejected alternatives have since become more viable
6. **Report** -- produce findings sorted by priority.
## Output Format
```
ADR Review | scope: {all|ADR_ID} | checks: {staleness,outcomes,alternatives}
## Summary
- Total ADRs reviewed: {N}
- Current and valid: {N}
- Needs attention: {N}
- Superseded (unmarked): {N}
## Findings
### {ADR_ID}: {title}
- **Status**: {current|stale|superseded|incomplete}
- **Issue**: {description of the finding}
- **Evidence**: {what indicates this finding}
- **Recommendation**: {action to take}
## ADR Health
| ADR | Date | Status | Staleness | Outcomes | Alternatives |
|-----|------|--------|-----------|----------|--------------|
## Recommendations
1. {prioritized action items}
## No further action needed | {N} ADRs need updates
```
## Skill Chains
| After this skill... | Consider... |
|--------------------|-------------|
| Stale ADRs found | `[decision-log]` to create updated decisions |
| Tech debt from old decisions | `[tech-debt]` to quantify remediation effort |
| Patterns in decision-making | `[retrospective]` to reflect on decision quality |From hummbl-io/agent-skills, Apache-2.0.
More from hummbl-io/agent-skills
- 0.565score
ab-test-analyzer
hummbl-io
Analyze A/B test results for statistical significance, effect size, and practical importance.
SkillAFreshness: AClaude Code +9 - 0.565score
aar-followthrough
hummbl-io
Run AFTER [aar] completes to elaborate and plan every §7 recommendation into an owned, verifiable goal that feeds into [goal-selection].
SkillAFreshness: AClaude Code +9 - 0.565score
agent-grade
hummbl-io
Grade an agent's work on a 100-point rubric that scores verified, authorized state change — not activity, token volume, or apparent confidence.
SkillAFreshness: AClaude Code +9 - 0.558score
a11y-fix
hummbl-io
Generate specific fixes for accessibility audit findings with code patches
SkillAFreshness: AClaude Code +9 - 0.558score
agent-memory
hummbl-io
Design agent memory systems with short-term, long-term, episodic, and semantic memory and retrieval strategies
SkillAFreshness: AClaude Code +9 - 0.558score
agent-metrics
hummbl-io
Aggregate agent performance metrics from bus, git, and CI history
SkillAFreshness: AClaude Code +9 - 0.558score
absence-audit
hummbl-io
Find what's MISSING from a system -- unhandled cases, missing tests, absent monitoring, silent failures.
SkillAFreshness: AClaude Code +9 - 0.558score
aar
hummbl-io
Generate an After Action Report with Base120 references and receipts.
SkillAFreshness: AClaude Code +9 - 0.558score
agent-audit
hummbl-io
Audit a specific agent's bus activity, commit history, trust score, and guardrail compliance.
SkillAFreshness: AClaude Code +9 - 0.558score
agent-compare
hummbl-io
Side-by-side comparison of agent outputs on identical tasks — quality, speed, cost, accuracy
SkillAFreshness: AClaude Code +9 - 0.558score
agent-design
hummbl-io
Design agentic workflows -- tool selection, loop structure, guardrails, memory, termination conditions
SkillAFreshness: AClaude Code +9 - 0.558score
agent-cost-track
hummbl-io
Track per-agent token usage and API costs with budget alerts and cost attribution
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Sep 27, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/hummbl-io/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hummbl-io
- 0.565score
ab-test-analyzer
hummbl-io
Analyze A/B test results for statistical significance, effect size, and practical importance.
SkillAFreshness: AClaude Code +9 - 0.565score
aar-followthrough
hummbl-io
Run AFTER [aar] completes to elaborate and plan every §7 recommendation into an owned, verifiable goal that feeds into [goal-selection].
SkillAFreshness: AClaude Code +9 - 0.565score
agent-grade
hummbl-io
Grade an agent's work on a 100-point rubric that scores verified, authorized state change — not activity, token volume, or apparent confidence.
SkillAFreshness: AClaude Code +9 - 0.558score
a11y-fix
hummbl-io
Generate specific fixes for accessibility audit findings with code patches
SkillAFreshness: AClaude Code +9 - 0.558score
aar
hummbl-io
Generate an After Action Report with Base120 references and receipts.
SkillAFreshness: AClaude Code +9 - 0.558score
agent-audit
hummbl-io
Audit a specific agent's bus activity, commit history, trust score, and guardrail compliance.
SkillAFreshness: AClaude Code +9
Cite this page
adr-review skill. Agent Mart. https://agentmart.dev/skills/hummbl-io-adr-review (last updated 2026-10-24)