For AI agents#

opsward ships artifacts for coding agents alongside its code. This page lists them, says where each lives in the repository, and points at the machine-readable copies of this documentation.

Skills#

Skills are folders holding a SKILL.md (the Agent Skills format): a description that tells an agent when to use it and a body with the procedure. Install one into your agent with gh skill (any host: --agent claude-code, copilot, cursor, codex, gemini), or use the copy bundled in the wheel.

opsward#

Run opsward to assess and improve this project’s AI agent setup. Use when the user says ‘opsward’, ‘check my setup’, ‘improve my AI config’, or wants a full audit and remediation.

Source: .claude/skills/opsward.

opsward-add-recommendation#

Add a tech-stack→skill mapping to opsward’s recommendation engine in recommend.py, so opsward recommend suggests an ecosystem skill when it detects a dependency or framework (e.g. Supabase, FastAPI, Tailwind). Use when extending the curated _RECOMMENDATIONS list, adding a new detection signal, or changing where recommended skills are sourced from.

Source: .claude/skills/opsward-add-recommendation.

opsward-add-scoring#

Add or adjust opsward’s quality scoring — a CLAUDE.md sub-dimension, a whole weighted component, or the skill/spec validation rules — in score.py. Use when changing how opsward diagnose grades a project, tuning weights or point thresholds, adding a new ComponentScore, or modifying validate_skill_spec. Explains the pure-function contract, the weighting math, and the constants to keep balanced.

Source: .claude/skills/opsward-add-scoring.

opsward-add-template#

Add or edit a generation template in opsward — a doc template (architecture.md, testing.md, …), an installable skill (SKILL.md), or an agent definition — and wire it into generate.py so opsward produces it. Use when adding a new artifact opsward should scaffold into target projects, adding a template variable, or changing what opsward generate / install-skills emit. Covers string.Template rules and the python/jsts/shared layout.

Source: .claude/skills/opsward-add-template.

opsward-dev#

Contributor guide for developing opsward itself — its architecture, hard invariants, and where each kind of change goes. Use when modifying opsward’s own source (scan/score/generate/maintain/recommend/cli), adding a template, scoring dimension, or skill recommendation, or when unsure which module owns a change. NOT for running opsward on a target project (use the opsward skill for that).

Source: .claude/skills/opsward-dev.

opsward-diagnose#

Diagnose the health of this project’s AI agent setup. Use when the user asks to check, audit, or score the project’s CLAUDE.md, skills, docs, or agent configuration.

Source: .claude/skills/opsward-diagnose.

opsward-generate#

Generate missing AI setup artifacts for this project. Use when the user asks to scaffold, create, or bootstrap CLAUDE.md, docs, skills, or agent configuration.

Source: .claude/skills/opsward-generate.

opsward-maintain#

Check documentation and AI setup for staleness, drift, or inconsistency. Use when the user asks to maintain, refresh, or update project docs and AI configuration.

Source: .claude/skills/opsward-maintain.

Subagents#

Subagents are Markdown files with a frontmatter (name, description, tools) and a system prompt as the body. Copy one into your project’s .claude/agents/ (or your agent host’s equivalent) to delegate the task it describes.

setup-auditor#

Read-only diagnostic agent that audits the project’s AI setup (CLAUDE.md, skills, docs, rules). Use when you want to check the health of the project’s agent configuration without making changes.

Source: .claude/agents/setup-auditor.md.

Instruction files#

Files agents read before working in this repository.

  • CLAUDE.md: read by Claude Code

  • AGENTS.md: read by Codex, Copilot, Cursor and other agents

Machine-readable documentation#

This site publishes the same documentation in forms that fit an agent’s context window:

  • llms.txt: an index of every page with a one-line description (llms.txt format)

  • opsward.md: the whole documentation as one Markdown file

  • <page>.html.md: a rendered Markdown twin of every page, advertised from each page’s <head> with <link rel="alternate" type="text/markdown">

  • objects.inv: the Sphinx inventory: a symbol-to-URL index (sphobjinv convert plain objects.inv -)