From agent-harness-kit
Use this skill whenever a decision is made about architecture, dependencies, frameworks, naming conventions, or layer order. Creates a numbered ADR (Architecture Decision Record) in `.harness/docs/adr/` in the canonical Nygard format. Always invoke this before changing layer order, adding a layer, swapping a major dependency, or introducing a new external service.
How this command is triggered — by the user, by Claude, or both
Slash command
/agent-harness-kit:SKILLtemplates/.claude/skills/add-adr/This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
## When to use ADR Use this skill when making architectural decisions. See `/feature-intake` for the complete list of ADR triggers. **Quick reference - ADR required for:** - New layer, domain, or provider - Breaking API changes - Security/auth boundary changes - Data model migrations - Performance-critical path changes - Deployment strategy changes **Rule of thumb:** If the decision affects multiple teams, has long-term implications, or sets a precedent → create an ADR. For the complete list of triggers with examples, see the "ADR Triggers (Explicit)" section in `/feature-intake` SKILL....
Use this skill when making architectural decisions. See /feature-intake for the complete list of ADR triggers.
Quick reference - ADR required for:
Rule of thumb: If the decision affects multiple teams, has long-term implications, or sets a precedent → create an ADR.
For the complete list of triggers with examples, see the "ADR Triggers (Explicit)" section in /feature-intake SKILL.md.
.harness/docs/adr/ and pick the highest existing
number + 1 (zero-padded to 4 digits)..harness/docs/adr/{NNNN}-{kebab-title}.md with the
sections below..harness/config.json AND the structural-test config in the
same commit as the ADR..harness/docs/architecture.md.# ADR <NNNN> — <title>
- **Status:** proposed | accepted | superseded by <link>
- **Date:** YYYY-MM-DD
- **Deciders:** <names or "project owner">
## Context
<What forces are in play? What constraints? What did we learn that triggered this?>
## Decision
<What we decided. Single sentence then a list.>
## Consequences
Positive: ...
Negative: ...
## Alternatives considered
- <alternative>: <why rejected>
- <alternative>: <why rejected>
### ADR: <NNNN>-<slug>
### Status: <status>
### Configs updated: <list or "none">
### .harness/docs/architecture.md updated: yes/no
/SKILLResolves GitHub issue via isolated worktree, TDD workflow, and auto-closing PR creation.
/SKILLCreates conventional git commit from conversation intent using git-agent and pushes to remote. Accepts optional Claude model name for co-author.
/SKILLSurfaces current session task from state file, evaluates clarity (prompts for clarification if needed), assesses completion, and verifies if fully done.
npx claudepluginhub tuanle96/agent-harness-kit --plugin agent-harness-kit