Initializes tenant-tail sessions by running the standardized AGENTS.md bootstrap protocol.
Install
mkdir -p .claude/skills/init-stagecraft-ing && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12051" && unzip -o skill.zip -d .claude/skills/init-stagecraft-ing && rm skill.zipInstalls to .claude/skills/init-stagecraft-ing
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Initialize a tenant-tail session by executing the cross-agent New Sessions protocol declared in AGENTS.md.Key capabilities
- →Read the New Sessions section from AGENTS.md
- →Execute the protocol using parallel tool calls
- →Emit a structured summary as prescribed by the protocol
- →Build the verify CLI from source if the binary is missing
- →Read governance state through the pinned spec-spine
How it works
The skill reads the New Sessions protocol from AGENTS.md and executes the described steps using Claude Code's parallel tool calls to bootstrap the environment.
Inputs & outputs
When to use init
- →Initialize a new session
- →Bootstrap tenant-tail environment
- →Verify governance state
About this skill
/init: session bootstrap
Thin Claude-Code dispatcher. The canonical protocol lives in
AGENTS.md § New Sessions under the AAIF/Linux Foundation
cross-agent standard.
What to do
- Read
AGENTS.md: the section from## New Sessionsinclusive to the next##heading exclusive. That section is the step list. - Execute the protocol described there using Claude Code's parallel tool calls where the protocol says "dispatch simultaneously".
- Emit the structured summary the protocol prescribes (the
## initialized: tenant-tailblock).
This dispatcher does not duplicate the step list. AGENTS.md is the single source of truth read by Claude Code, Codex CLI, Cursor, Copilot, and any future agent.
The protocol builds the verify CLI from source (cargo build --release -p tenant-tail-cli) and reads governance state through the pinned
spec-spine (npx --no-install spec-spine ..., the dogfood dependency).
If the binary is missing, build it and continue.
When not to use it
- →When the New Sessions protocol is not declared in AGENTS.md
- →When a different session initialization protocol is required
Limitations
- →It does not duplicate the step list; AGENTS.md is the single source of truth.
- →It is a thin Claude-Code dispatcher.
How it compares
This skill centralizes the session initialization process by referencing a single AGENTS.md protocol, unlike manual setups that might involve disparate instructions.
Compared to similar skills
init side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| init (this skill) | 0 | 1mo | No flags | Beginner |
| skillshare | 1 | 2mo | Review | Intermediate |
| subtask | 3 | 6mo | Review | Advanced |
| agent-swarm-issue | 1 | 6mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
skillshare
runkids
Syncs skills across AI CLI tools (Claude, Cursor, Windsurf, etc.) from a single source of truth. Use when: "sync skills", "install skill", "search skills", "list skills", "show skill status", "backup skills", "restore skills", "update skills", "new skill", "collect skills", "push/pull skills", "add/remove target", "find a skill for X", "is there a skill that can...", "how do I do X with skills", "skillshare init", "skillshare upgrade", "skill not syncing", "diagnose skillshare", "doctor", or any skill/target management across AI tools.
subtask
zippoxer
Parallel task orchestration CLI that dispatches work to AI workers (via Claude Code) in isolated git workspaces. Use when the user wants to draft, create, run, or manage tasks, delegate tasks to workers/subagents, or mentions subtask or Subtask.
agent-swarm-issue
ruvnet
Agent skill for swarm-issue - invoke with $agent-swarm-issue
monitor-tweet
ArthTech-AI
Run the tweet-to-toolkit pipeline on a tweet. Flow: (1) triage+feasibility, (2) ALWAYS show findings and BOTH repo options to user, (3) user approves target + direction, (4) build auto-starts, (5) review auto-starts, (6) if APPROVED, gh pr create auto-runs. The ONLY human gate is step 2 — everything
unshelve
WingedGuardian
>
cursor-multi-repo
jeremylongshore
Manage work with multiple repositories in Cursor. Triggers on "cursor multi repo", "cursor multiple projects", "cursor monorepo", "cursor workspace". Use when working with cursor multi repo functionality. Trigger with phrases like "cursor multi repo", "cursor repo", "cursor".