jacobpevans/agentsmd-authoring
project-standards/skills/agentsmd-authoring/SKILL.md
Use when editing agentsmd files, creating skills/agents/rules, or working in ai-assistant-instructions
$ install --global
skillsauthnpx skillsauth add jacobpevans/claude-code-plugins agentsmd-authoringInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 7:52 PM51.2s1 file scanned
SKILL.md
- name:
- agentsmd-authoring
- description:
- Use when editing agentsmd files, creating skills/agents/rules, or working in ai-assistant-instructions
AgentsMD Authoring Standards
File Structure
agentsmd/ # Single source of truth
├── AGENTS.md # Main entry point
├── rules/ # Auto-load every session (via .claude/rules symlink)
├── skills/ # On-demand (via .claude/skills symlink)
├── agents/ # Task subagents (via .claude/agents symlink)
└── workflows/ # Development workflow docs
.copilot/, .claude/, .gemini/ # Vendor dirs — symlinks only, no duplicates
Token Targets
- Target: 500 tokens per file
- Maximum: 1,000 tokens per file
- CLAUDE.md additions: bare minimum — link to rules/skills for details
- Single-purpose: each skill/agent/rule does one thing
Two-Tier Architecture
| Tier | Location | Purpose |
| --- | --- | --- |
| Agents | .claude/agents/ | Task execution — single-responsibility workers |
| Skills | agentsmd/skills/ | Canonical patterns — reusable rules/decision trees |
Agents reference skills for patterns. Skills define the "right way" to do something. Agents do NOT duplicate skill logic — they reference it.
Naming Convention
- Skills:
noun-pattern(e.g.,permission-patterns) - Agents:
noun-doer(e.g.,permissions-analyzer)
Frontmatter Templates
Skill:
---
name: skill-name
description: Pattern description
---
Agent:
---
name: agent-name
description: Action-focused description
model: haiku # or sonnet/opus
author: JacobPEvans
allowed-tools: [list of tools]
---
Cross-Referencing
- In CLAUDE.md: Use
@path/to/fileto compose content inline. Use markdown links only for conditional "see X if relevant" references. - In agents/skills/rules: Reference by name
(e.g., "the code-standards rule"). Rules in
.claude/rules/auto-load.
Vendor Config Standard
Vendor directories contain symlinks only. All canonical content lives in
agentsmd/. DRY — never duplicate across vendors.
Rules in agentsmd/rules/ auto-load every session via .claude/rules
symlink. Keep rules focused and under 1,000 tokens.
Related Skills
- skills-registry (project-standards) — Use when looking up available tools, skills, commands, agents, or plugins
- workspace-standards (project-standards) — Use when setting up or managing multi-repo workspaces
Related Skills
jacobpevans/nix-tool-policy
tools
VerifiedTrustedCommunity
Use when installing or choosing CLI tools in a Nix flake repo, editing flake.nix or home-manager config, or when tempted to pip/pipx/uv/brew/npm install anything. Tools come from the dev shell or nix shell — never ad-hoc package managers.
3SKILL.mdUpdated Jun 11, 2026
jacobpevans/shared-workflow-org-refs
testing
VerifiedTrustedCommunity
Use when creating or editing GitHub Actions workflows that call reusable workflows (uses: OWNER/repo/.github/workflows/...) — org owner references must be the literal current org, and shared-CI homes are under dryvist.
3SKILL.mdUpdated Jun 11, 2026
jacobpevans/pre-commit-architecture
development
VerifiedTrustedCommunity
Use when adding or editing .pre-commit-config.yaml, wiring pre-commit hooks into a repo, scaffolding a new repo's lint/hook setup, or deciding where a hook or shared lint config should live. Covers the canonical nix-devenv/dryvist-.github architecture, profiles, and consumer patterns.
3SKILL.mdUpdated Jun 11, 2026
jacobpevans/refresh-repo
testing
VerifiedTrustedCommunity
Check PR merge readiness, sync local repo, cleanup stale worktrees; optional cross-repo sweep and stale-branch prune modes
3SKILL.mdUpdated Apr 28, 2026