All 94 skillsWorkflow6 of 15
stryx:config
When Claude Code's own setup needs checking or tidying: CLAUDE.md, settings, permissions, memory.
/stryx:configInside its piece: 15 specks, one for each file on its shelf. Its fourteen group-mates glow on the open book behind it. The light splits toward indigo, the band of Workflow.
In numbers
counted 2026-10-12 in the installed set- 11reference files
- 2helper scripts
- 15files in the skill
- 215KB on disk
- 7chapters
- 4agents work by this book
Use it when
in the skill’s own wordsWhen checking, auditing, tidying, setting up or optimizing Claude Code configuration
- CLAUDE.md
- CLAUDE.local.md
- ~/.claude/settings.json and settings.local.json
- permissions
- .claude/rules
- MEMORY.md and memory topic files
- enabled plugins
- hook registrations
- When the user says
- "config health"
- "project health"
- "check project"
- "audit context"
- "audit memory"
- "tidy permissions"
- "clean settings"
- "add python permissions"
- "setup project"
- "kickoff"
- "bootstrap"
- "init project"
- "restructure CLAUDE.md"
- "context budget"
- "why does this rule always load"
- "is the stryx install right"
- "adopt me"
- "adopt this"
- "merge training"
- "install package"
- "sync config"
- gives a config zip or folder to merge
- When moving config between Home, Office or another username
- When asked about compaction thresholds or context usage
Not for
another skill does it- Creating a skill, agent, command or hook→ stryx:skill-forge
- Saving a lesson→ stryx:learn
- Hook scripts→ stryx:shell
- Writing a handoff or fresh start→ stryx:handoff
On its shelf
15 files, 215 KB- references/11
- scripts/2
- SKILL.md1
- evals/1
Inside the book
7 chapters, by title only- Pick the mode
- The layers in brief
- What belongs where
- Core procedure
- Autonomy
- Verification gates
- Symptoms and where to look
Its helpers
4 agents work by this book- stryx:project-status-analystYou ask "where are we really": it compares the plans with the code and the git history.
- stryx:prompt-engineerWhen a prompt for Claude needs writing or tightening: a skill, an agent, a CLAUDE.md.
- stryx:security-agentWhen a project or a change needs a security audit with evidence.
- stryx:toolchain-guardianWhen the build settings of a JavaScript or TypeScript project should be checked as one system.
Works with
the skills it names most- stryx:learn→You say "remember this" or wrap up a session: the lessons are saved for next time.
- stryx:skill-forge→When creating or changing a skill, agent, slash command or hook, or a skill did not fire.
- stryx:handoff→When work must continue in a later session: it saves where things stand.
- stryx:shell→When writing or fixing a script or a tricky command line: PowerShell, Git Bash, batch files.
- stryx:ai-power→When you are not sure which skill fits, or you say "load aipower": it is the map of all skills.
- stryx:devops→When work must be committed, pushed, made a pull request, released or packaged.
Claude loads it by itself when the moment comes; by hand, type the line at the top. It comes with the whole set: Installs all 94 skills, 32 agents and the brain program as one set. The skill’s own text is private source and is not shown here.