Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Adr

ASecurity

- Status: accepted - Date: 2026-09-29

21 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentsgit

Works with

claude codemcp

Security Analysis

A100/100

Pro scans all 21 files and shows the line behind each finding

Scanned 10/4/2026

$npx -y skills add melodic-software/claude-code-plugins --skill adr --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Adr?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Adr
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/melodic-software-adr-claude-code-plugins/badge)](https://www.skillsdirectory.com/skills/melodic-software-adr-claude-code-plugins)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
0001-defer-gitbook-as-knowledge-vault-backend.md
# Place the machine profile as a harness-ops skill

- Status: accepted
- Date: 2026-09-29

## Context

The [machine profile design](https://github.com/melodic-software/claude-code-plugins/blob/9a0d6f5cf47098fa73bb4b8bb41336be1945c70e/docs/specs/machine-profile-design.md) (issue #4666) describes a
re-runnable profile that discovers host facts once, stores them, and hands each plugin's `setup`
the answers. The design needs one owner. Two placements were on the table: a skill in
`harness-ops`, or a new plugin.

Three existing surfaces sit next to it:

- `harness-ops` owns fleet state and ships `prerequisites` (probes the binaries each enabled plugin
  declares) and `inventory` (lists what this machine can invoke), the two skills the profile reads.
- `machine-health` owns severity, trend, history, and reporting for host findings.
- `harness-config` audits Claude Code configuration files and `harness-memory` audits the
  instruction and memory layer.

## Decision

Place the profile as a skill in `harness-ops`, not as a new plugin.

- **Why not a new plugin.** A new plugin would be a third owner of host facts beside
  `harness-ops` and `machine-health`, and would re-declare tool knowledge the `prerequisites.json`
  manifests already hold.
- **machine-health.** The profile is not a second drift checker. It is the host-fact document
  that machine-health's declared-configuration drift check consumes. The profile records observed
  facts, verdicts, and provenance, and assigns no severity and keeps no history. machine-health
  reads the document and reports findings in its own schema, and does no option discovery. Until
  that check exists, the profile's `diff` is the only consumer.
- **harness-config and harness-memory.** They audit files Claude Code reads (settings, hooks, MCP
  configuration, `CLAUDE.md`, rules, auto-memory) for correctness against upstream docs. The
  profile records what the host contains (binaries, identity domains, tree boundaries, roots),
  not whether a Claude Code file is correct. Where a value belongs to one of those surfaces, the
  profile records the observation and that surface's audit stays the judge of the file.

## Status scope

Accepted. The skill, its scripts, its tests and the `harness-ops` version bump are authorized. The
invocation-mode change (class (ii) and the hidden `setup` skills) and any change to the setup
contract are not part of this decision.

## Consequences

The skill's directory is under `plugins/harness-ops/skills/`. A move to a new plugin would
supersede this record.

Attribution

melodic-softwaremelodic-software
View sourceSee grades on GitHubMore from melodic-software →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →