teamctl
01Plugin Claude Code
teamctl — persistent AI agent teams, declared in YAML and launched from a chat with Claude.
Plugin Claude Code
teamctl — persistent AI agent teams, declared in YAML and launched from a chat with Claude.
Agent Claude Code
Scans the Backlog column of teamctl's GitHub Project board and triages each item for hygiene — already-shipped, duplicate, or stale — against the repo and the linked issue. Use on a backlog grooming sweep, when the PM wants to know what's dead weight before the owner promotes work to Ready. Returns a proposal list…
Agent Claude Code
Moves one card's Status on the teamctl GitHub Project board (#6, owner Alireza29675) by self-discovering the project, field, option, and item IDs and editing it with gh. Use when an issue or PR needs its board status changed — "move.
Agent Claude Code
Maps the slice of the teamctl workspace a task will touch, before any code is written. Use as an engineer's first move on every new ticket. Returns a short orientation brief — files, flow, seams, gotchas — across crates, not edits.
Agent Claude Code
Adversarial review of a teamctl diff or PR — picky, specific, on the side of the product. Use for a hard self-review before an engineer asks a human, or when a peer wants eyes on a branch. Returns severity-ranked findings plus a verdict. Read-only; never edits.
Agent Claude Code
Confirms a ticket is truly safe to compact — its PR is merged on origin and its session note exists on disk. Use as the final gate before an engineer self-compacts a finished ticket. Returns clear or blocked with the specific reason. Read-only; it verifies, it never fixes.
Agent Claude Code
Resolves the right Co-Authored-By trailer for a ticket by identifying who opened the source GitHub issue. Use before committing work that closes an external contributor's issue. Returns a ready-to-paste trailer, or "internal — skip" when the opener is a teammate. Lookup only; it never commits.
Agent Claude Code
Reads teamctl's docs, README, and site copy with fresh eyes and flags where a real reader would stumble. Use when the writer (Neda) ships or revises docs, or wants a friction pass before publish. Returns a prioritized friction list with exact file and line pointers. Read-only — flags problems, never rewrites the prose.
Agent Claude Code
Assesses whether a proposed feature is buildable in the teamctl codebase, and at what effort and risk. Use when Sage needs a grounded build/scope/skip read before an idea becomes a ticket. Returns Verdict/Approach/Effort/Risks/De-risk. Reads the real code; never edits it.
Agent Claude Code
Samples teamctl's running state — mailbox.db size, live tmux session count vs configured roster, open painpoint counts, recent supervisor log lines — and flags anomalies against the known baseline. Use when Otto wants a passive background health sweep of the dogfood team. Returns a 2-4 line summary (all-nominal or the…
Agent Claude Code
Implements a well-scoped, clearly-specified change in the teamctl workspace. Use when an engineer has decided WHAT to build and wants focused hands on a defined slice of a crate. Returns the change plus a verification summary; the owning engineer keeps the judgment and review.
Agent Claude Code
Writes a clear, human PR body for teamctl from the diff. Use when an engineer is opening a PR on a T-NNN branch. Returns ready-to-paste markdown — what, why, how to verify. No AI attribution; preserves an external issue-opener's Co-Authored-By trailer.
Agent Claude Code
Reads an open teamctl pull request and explains it in plain, owner-facing terms so the PM can relay it for approve/merge. Use when an engineer says a PR is ready, or the PM needs a non-technical read of a PR. Returns a short What/Why/Risk/Status/Link summary, with a clear flag if it's not actually ready. Read-only …
Agent Claude Code
Turns a settled idea conversation into a clean teamctl PRD draft that maps cleanly onto a GitHub issue. Use after Sage and the owner agree an idea is ticket-shaped. Returns the draft text plus the path it was written to. Drafts only; does not file the issue or write code.
Agent Claude Code
Checks whether an idea already exists as a teamctl GitHub issue, an in-repo feature, or established prior art elsewhere. Use before Sage files a ticket or tells the owner "has anyone built this?" — go check instead of guessing. Returns exists?/how-it-differs/duplicates. Read-only; never files or edits.
Agent Claude Code
Researches prior art, competitors, positioning, and user expectations for a teamctl feature or messaging angle, with citations. Use when Neda needs grounded market/user context before writing docs, a launch post, or a positioning take. Returns a tight cited brief (What-exists / Users-expect / Opportunity /…
Agent Claude Code
Runs teamctl's suite and exercises the change like a skeptical user, reporting what actually happens. Use before an engineer marks a PR ready, or when Hugo wants a manual-test pass on a branch. Returns a pass/fail verdict with exact repro steps. Reports findings; never edits code.
Agent Claude Code
Reads the "Ready" column of the teamctl GitHub Project board (#6, owner Alireza29675) and condenses each card to a single line so the team knows what to pick up next. Use when the PM (Hugo) is routing work, or an engineer is scanning for the next Ready task to start in a fresh worktree. Returns a tight list of Ready…
Agent Claude Code
Writes a durable post-merge session note for a shipped ticket into the engineer's state dir. Use right after a PR merges, before the engineer compacts. Returns the exact path of the note it wrote. Captures only; never touches code, branches, or the mailbox.
Agent Claude Code
Files an approved teamctl PRD as a GitHub issue with the right label, using gh. Use ONLY after Sage and the owner give the explicit go-ahead on a draft. Returns the created issue URL. Files exactly the approved draft; never edits drafts or writes code.
Agent Claude Code
Writes or extends Rust tests for a change in the teamctl workspace, in the same PR as the code. Use when an engineer needs real coverage — happy path, edges, failure modes. Returns the tests plus a coverage note. Follows the repo's existing test patterns.
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing no-merge.sh. From Alireza29675/teamctl.
Hook Claude Code
Runs after a tool call finishes, executing audit.sh. From Alireza29675/teamctl.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing audit.sh. From Alireza29675/teamctl.