Team Implement

Team Implement — Execute the Plan

Run the IMPLEMENT phase. Three internal sub-steps:

1. Test-first — test-architect writes failing acceptance tests
2. Slice execution — implementer executes vertical slices with

per-slice commits

1. Code review — 5 parallel reviewers + aggregate hard-gate retry loop

Input

$ARGUMENTS is the artifact directory: docs/plans//. If empty, the discovery block below resolves it.

The agents read:

• $ARGUMENTS/plan.md — file-level steps and per-slice tests
• $ARGUMENTS/structure.md — slice ordering and verification checkpoints
• $ARGUMENTS/design.md — context for what each test should assert
• $ARGUMENTS/repos.md — repo scope (only present when the topic spans

more than one repository); the implementer cd's between worktrees as the plan steps require

• $ARGUMENTS/task.md — intent (for the implementer when in standalone mode)

Resolve the artifact directory by running this self-contained block (one bash call — agent threads reset cwd between calls):

# Three-tier artifact-directory discovery (archetype A).
# ID_RE + PHASE_FILES canonical from hooks/session-start-recover.mjs.
# PHASE_FILES recency mirrors findActiveTopic() in session-start-recover.mjs.
# NOTE: this block is duplicated across 8 skills by design (see docs/architecture.md); future: shared discover-topic.sh.
ID_RE='^([A-Za-z][A-Za-z0-9_]*-[0-9]+|[0-9]{4}-[0-9]{2}-[0-9]{2})-[a-z0-9][a-z0-9-]*$'
PHASE_FILES="task questions research design structure plan"
PRED="plan.md"            # predecessor artifact this skill consumes
# Tier 1 — explicit: $ARGUMENTS names an existing dir → use verbatim.
if [ -n "$ARGUMENTS" ] && [ -d "$ARGUMENTS" ]; then
  echo "$ARGUMENTS"; exit 0
fi
# Tier 2 — discover: newest ID_RE dir under docs/plans/ that holds PRED.
best=""; best_mtime=-1
# Assumes cwd is the repo/worktree root (where docs/plans/ lives).
for dir in docs/plans/*/; do
  name="$(basename "$dir")"
  printf '%s' "$name" | grep -qE "$ID_RE" || continue   # ID_RE filter
  [ -f "$dir$PRED" ] || continue                        # predecessor filter
  m=-1
  for p in $PHASE_FILES; do
    f="$dir$p.md"
    [ -f "$f" ] || continue                             # skip racing/absent
    s="$(stat -f %m "$f" 2>/dev/null || stat -c %Y "$f" 2>/dev/null)" || continue
    [ "${s:-0}" -gt "$m" ] && m="$s"                    # max-mtime over PHASE_FILES
  done
  [ "$m" -gt "$best_mtime" ] && { best_mtime="$m"; best="$dir"; }
done
[ -n "$best" ] && { echo "$best"; exit 0; }
# Tier 3 — none found: print nothing → fall to AskUserQuestion (prose below).

• If the block printed a path, use it as $ARGUMENTS for the rest of this

skill (tier 1 explicit arg, or tier 2 discovery). When the path came from tier 2 (no explicit arg), announce the resolved directory to the user before proceeding, so an auto-picked topic is never silent.

• If the block printed nothing (tier 3 — no directory under docs/plans/

holds plan.md), do not hard-error. Fire AskUserQuestion with a Setup header and labeled options:

• Run the producer — run /team-plan docs/plans// to produce the

missing plan.md.

• Provide a path — the user supplies the docs/plans// directory

directly (run ls docs/plans/ to find your topic directory).

• Describe the task — the user types a 1–2 sentence description of what

to implement. Derive a fresh ` (date-prefixed kebab slug, the same way the questioner does), create docs/plans//task.md` from that description, then proceed from the new directory in standalone mode.

Standalone mode — the resolved or provided directory has no plan.md, so the run starts from that directory's task.md instead. It triggers whenever tier 1 (explicit $ARGUMENTS), a user-provided path, or a freshly derived directory (from Describe the task) names a docs/plans// that lacks plan.md. The directory is always defined in this case. If $ARGUMENTS/plan.md does not exist in it, run test-architect → implementer → reviewers from $ARGUMENTS/task.md alone.

Coordinate progress via TodoWrite. Seed: Test-architect → Mechanical gate → Implementer (per slice) → Review round 1. See skills/progress-tracking/SKILL.md for the per-step tracking convention agents follow within each phase.

Worktree Check

Before any agent dispatch, decide where to work:

1. Read $ARGUMENTS/repos.md if present. When present, you are in

multi-repo mode. Confirm a worktree exists in every listed repo (read the ## Worktrees section). If any are missing, tell the user to run /team-worktree [docs/plans//] (the path is optional — discovery resolves it) and stop.

1. Run git rev-parse --absolute-git-dir. If the path contains

/worktrees/, you are already inside a Claude Code worktree — proceed in place. In multi-repo mode this should be the home repo's worktree; the implementer cd's into the other repos' worktrees as the plan steps require.

1. If you are in the main working tree, use AskUserQuestion to ask

where to run the implementation. Use a single question with a Worktree header and these options:

• Worktree (Recommended) — isolate this implementation in a new

git worktree (or set of worktrees in multi-repo mode).

• In-place — implement on the current branch in the main working

tree.

• On Worktree — derive `` from the resolved directory, create the

worktree(s) via /team-worktree [docs/plans//], tell the user the home worktree path, and ask them to re-run /team-implement [docs/plans//] from that directory.

• On In-place — proceed. (In-place is single-repo only — refuse

in-place if repos.md is present and tell the user that multi-repo work requires worktrees.)

Execution

1. Verify $ARGUMENTS/plan.md (resume mode) or bootstrap

$ARGUMENTS/task.md (standalone mode).

1. Dispatch test-architect → produces failing tests. In standalone

mode it derives acceptance criteria from $ARGUMENTS/task.md instead of structure.md.

1. Mechanical gate — confirm all tests fail with assertion errors

(not crashes). On crash, fix test infrastructure before proceeding.

1. Dispatch implementer → executes slices with per-slice commits. In

standalone mode it works from $ARGUMENTS/task.md and the failing tests.

1. Dispatch 5 reviewers in parallel: code-reviewer,

security-reviewer, technical-writer, ux-reviewer, verifier.

1. Aggregate gate — sort every finding into a severity tier (see

skills/code-review/SKILL.md → "Severity Tiers and the Auto-Fix Boundary"):

• Blocking — security-review CRITICAL/HIGH, any verification failure,

code-review REQUEST CHANGES, any issue (blocking) comment.

• Major — suggestion (non-blocking), security MEDIUM, ux-reviewer

REQUEST CHANGES.

• Minor and below — nitpick (non-blocking), security LOW, doc gaps,

any COMMENT-level note.

1. While any Blocking or Major finding remains:

• Record the typed failure class(es) (security, lint, typecheck, build,

test, review, suggestion, ux).

• Append Review round to the TodoWrite ledger.
• If round count /`"**

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: bostonaholic
• Source: bostonaholic/team
• License: MIT
• Homepage: https://team.bostonaholic.dev

Install and usage instructions live in the source repository linked above.