Install
$ agentstack add skill-bensheridanedwards-architectplaybook-install-architect-playbook-globally ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
/install-architect-playbook-globally
Copy every skill folder from this architect-playbook repository into ~/.claude/skills/. After running this, every architect-playbook slash command works in every Claude Code session on the machine, regardless of which project is open.
This skill is the machine-wide counterpart to [/install-architect-playbook-locally](../install-architect-playbook-locally/SKILL.md). The mechanics are the same; only the destination differs.
Usage
/install-architect-playbook-globally # install or update every skill into ~/.claude/skills/
/install-architect-playbook-globally --dry-run # print the plan without copying anything
/install-architect-playbook-globally --force # overwrite destinations even if they appear newer
/install-architect-playbook-globally --include=name # install only one named skill (repeatable)
/install-architect-playbook-globally --exclude=name # skip a named skill (repeatable)
When to choose this over the local install
Use this skill when:
- You audit lots of different codebases and you do not want to re-install per project.
- You want a single canonical version of every skill on disk.
Prefer /install-architect-playbook-locally when:
- You want different projects to pin different versions of the playbook.
- You want the installed skills to live alongside the project in version control.
What this skill does
- Resolves the playbook root the same way
/install-architect-playbook-locallydoes. - Resolves the destination as
$HOME/.claude/skills/. Creates it if missing. - Asks for confirmation before overwriting any existing skill of the same name in
~/.claude/skills/. Global installs affect every Claude Code session on the machine, so the bar for overwriting must be higher than for a project-local install. - Enumerates source skills (every sub-folder with a
SKILL.mdexceptinstall-architect-playbook-locallyandinstall-architect-playbook-globally). - Copies each skill folder with
cp -R. The destination becomes a complete, self-contained copy. - Reports the result with the same format as the local installer.
Implementation steps
Step 1 — Resolve the playbook root
Same logic as /install-architect-playbook-locally. The skill file's parent of parent is the playbook root.
Step 2 — Resolve destination
DEST="$HOME/.claude/skills"
mkdir -p "$DEST"
Refuse to proceed if $HOME is unset or empty.
Step 3 — Enumerate skills
Same as the local installer. Exclude:
install-architect-playbook-locallyinstall-architect-playbook-globally- Any folder whose name begins with
.
Step 4 — Confirmation gate for overwrites
Before copying, list every destination that already exists:
The following skills already exist in ~/.claude/skills/ and will be overwritten:
- security-audit
- performance-audit
- graphify (NOT MANAGED BY THIS PLAYBOOK — will not be touched)
Continue? [y/N]
If the user does not answer y, abort. Do not overwrite skills the playbook does not own — for the architect-playbook this is everything except graphify. Detect ownership by checking whether the destination's SKILL.md name field matches a skill in the playbook source. Anything whose name is not in the source list is left alone.
Step 5 — Copy each skill
Same loop as the local installer, but writing to $HOME/.claude/skills/.
Step 6 — Print the summary
installed: pre-audit-setup
updated: security-audit
installed (stub): performance-audit
...
preserved: graphify (not managed by architect-playbook)
15 skills installed into ~/.claude/skills/
Open a new Claude Code chat (any project) to pick up the new slash commands.
Idempotency and safety rules
- Never overwrite skills the playbook does not own.
graphifyis the canonical example. - Re-running with no flags is safe.
- Refuses to write outside
$HOME/.claude/skills/. - Refuses to delete any directory in the destination — only
cp -Rover the top of it. --dry-runis honored.
Recommended commit message
This skill writes to your home directory, not your project, so there is nothing to commit. If you maintain ~/.claude as a tracked dotfiles repository, use:
chore: refresh architect-playbook skills in ~/.claude/skills/
What this skill explicitly does NOT do
- Install graphify.
- Modify any project's
.claude/settings.json. - Run any audit.
- Touch global Claude Code settings (
~/.claude/settings.json).
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: BenSheridanEdwards
- Source: BenSheridanEdwards/ArchitectPlaybook
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.