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 skill is triggered — by the user, by Claude, or both
Slash command
/agent-harness-kit:add-adrThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when making architectural decisions. See `/feature-intake` for the complete list of ADR triggers.
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- **Status:** proposed | accepted | superseded by 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
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub tuanle96/agent-harness-kit --plugin agent-harness-kit