Herdr Team Lead Skill

Process steps in order. Do not skip ahead.

Before any finish with enrolled work, reconcile the whole fleet under skills/herdr-teamlead/references/supervision.md. Continue observation or persist an authorized pause or handoff covering every active assignment. Keep user attention visible under skills/herdr-teamlead/references/attention.md.

Every step runs under the whole team contract. Read its core, every section above Team Composition, before Step 1:

skills/herdr-teamlead/references/team-operation.md Reading This Contract

Each step lists its step reference and contract sections to read before acting on it.

Each command resolves CP to the local or home plugin. Repeat its resolver in every call. Prose skills/... paths are relative to that root.

Step 1 — Determine the Mode

For catch-up or saved attention, follow the attention reference. For lesson curation, saved lead context, or a lead handoff, follow the working-memory reference and the contract's Working Memory:

skills/herdr-teamlead/references/attention.md
skills/herdr-teamlead/references/working-memory.md
skills/herdr-teamlead/references/team-operation.md Working Memory

Use the recorded state override or default; these commands need no live Herdr. Finish here after the requested operation. They grant no new task authority.

CP=.tessl/plugins/gamussa/coding-policy; [ -d "$CP" ] || CP="$HOME/$CP"
bash "$CP/skills/herdr-teamlead/teamlead.sh" catch-up [--state <state-file>]

CP=.tessl/plugins/gamussa/coding-policy; [ -d "$CP" ] || CP="$HOME/$CP"
bash "$CP/skills/herdr-teamlead/teamlead.sh" memory-show [--state <state-file>] [--id <stow-id>]

Read all attention pages before claiming completeness. Use the referenced owner commands for recording, resolution, lessons, and a new stow. Non-zero requires reporting its diagnostic; never fabricate missing history.

For saved retrospective requests, use the recorded state override or default. Read saved notes; report their date, coverage, conclusions, and path. Finish here.

CP=.tessl/plugins/gamussa/coding-policy; [ -d "$CP" ] || CP="$HOME/$CP"
bash "$CP/skills/herdr-teamlead/teamlead.sh" retro-list [--state <state-file>] [--task <task-id>] [--since <ISO-time>]

CP=.tessl/plugins/gamussa/coding-policy; [ -d "$CP" ] || CP="$HOME/$CP"
bash "$CP/skills/herdr-teamlead/teamlead.sh" retro-show [--state <state-file>] [--id <retro-id>] [--task <task-id>]

Both emit JSON; non-zero requires reporting the diagnostic. retro-show defaults to latest. For other requests, read HERDR_ENV before running scripts.

• Unset or empty — this skill does not apply. Say so and do the task directly, without roster calls, briefs, provisioning, reports, or simulated worker roles. Finish here.
• Set, with a team task, new retrospective, edit, or review of existing code — proceed immediately to Step 2. The lead never edits or reviews code itself, whatever the size.
• Set, with a question or one bounded read-only lookup — answer it directly and cite what you read: a file and line, or a command and its output. Edit nothing and dispatch nothing. Finish here.

Step 2 — Run the Preflight

For an explicit retrospective request, complete a new retrospective and finish here:

skills/herdr-teamlead/references/retrospectives.md
skills/herdr-teamlead/references/team-operation.md Retrospectives

Otherwise run the preflight on every round start, resume, and return from a later step, route its verdict, and record authority, ledger and staffing. Read first:

skills/herdr-teamlead/references/round-setup.md Step 2
skills/herdr-teamlead/references/team-operation.md Task Ledger
skills/herdr-teamlead/references/team-operation.md Retrospectives

Step 3 — Plan the Roles

Staff the fired triggers, validate any review partition, and plan the roles. Read first:

skills/herdr-teamlead/references/round-setup.md Step 3
skills/herdr-teamlead/references/team-operation.md Team Composition
skills/herdr-teamlead/references/team-operation.md Round Tiers
skills/herdr-teamlead/references/team-operation.md Review Before PR

A planned consultation also reads Specialist Consultations; a fix round also reads Fix Loops:

skills/herdr-teamlead/references/team-operation.md Specialist Consultations
skills/herdr-teamlead/references/team-operation.md Fix Loops

Step 4 — Build the Review Package

Reviewer and tester briefs need a review package bound to the recorded base and pushed head. Read first:

skills/herdr-teamlead/references/round-setup.md Step 4

Step 5 — Compose the Briefs

Resolve policy paths, write the values file, and compose. Read first:

skills/herdr-teamlead/references/round-setup.md Step 5
skills/herdr-teamlead/references/team-operation.md Assignment Reasoning
skills/herdr-teamlead/references/team-operation.md Working Memory

Step 6 — Provision the Worktrees

Prune every round, then provision every worktree a brief names. Read first:

skills/herdr-teamlead/references/round-setup.md Step 6
skills/herdr-teamlead/references/team-operation.md Writers and Checkouts

Step 7 — Label the Layout

Optional, once per team; skip an already named sidebar. Read first:

skills/herdr-teamlead/references/round-setup.md Step 7

Step 8 — Dispatch the Briefs

Send the planned briefs through apply. Read first:

skills/herdr-teamlead/references/round-dispatch.md Step 8
skills/herdr-teamlead/references/team-operation.md Dispatch Safety
skills/herdr-teamlead/references/team-operation.md Worker Launch Mode

CP=.tessl/plugins/gamussa/coding-policy; [ -d "$CP" ] || CP="$HOME/$CP"
bash "$CP/skills/herdr-teamlead/teamlead.sh" apply [--config <config-file>] \
  --assignments <plan-file> \
  --brief <role>=<path> [--brief <role>=<path>]... \
  --report <role>=<report> [--report <role>=<report>]... \
  --common <path-to-COMMON.md> --task <task-id> \
  [--fix-round <N>] [--retain-context | --retain-specialist | --no-clear] \
  [--correction-plan <id> --work <work.json>] [--dispatch-id <stable-id>]

Step 9 — Observe the Fleet

Watch every enrolled assignment, then confirm each report's delivery. Read first:

skills/herdr-teamlead/references/round-dispatch.md Step 9

A wait that ends in a stall also reads Stalled Workers:

skills/herdr-teamlead/references/team-operation.md Stalled Workers

CP=.tessl/plugins/gamussa/coding-policy; [ -d "$CP" ] || CP="$HOME/$CP"
bash "$CP/skills/herdr-teamlead/teamlead.sh" supervision-watch [--state <state-file>]

CP=.tessl/plugins/gamussa/coding-policy; [ -d "$CP" ] || CP="$HOME/$CP"
bash "$CP/skills/herdr-teamlead/wait-report.sh" --once \
  [--worktree <worker-checkout>] [--base <dispatch-base>] \
  [--since <dispatch-sent-at>] <agent-name> <report-path>

Step 10 — Gate the Round

Read every report in full, classify findings, and route the task to Step 2, Step 11, Step 19 or Step 20. Read first:

skills/herdr-teamlead/references/round-dispatch.md Step 10

Any blocking finding also reads Fix Loops:

skills/herdr-teamlead/references/team-operation.md Fix Loops

Step 11 — Compose the Judge Brief

Optional. No judge trigger — proceed to Step 18. A dispute or an exhausted allowance needs a judge; read these before Steps 11–15 and 17:

skills/herdr-teamlead/references/judge-round.md
skills/herdr-teamlead/references/team-operation.md Judge Seat

Step 12 — Re-measure the Shared Window

Run measure alone, not the preflight; the step reference routes the result:

skills/herdr-teamlead/references/judge-round.md Step 12

CP=.tessl/plugins/gamussa/coding-policy; [ -d "$CP" ] || CP="$HOME/$CP"
bash "$CP/skills/herdr-teamlead/teamlead.sh" measure

Step 13 — Plan the Judge Seat

Plan the pinned judge against Step 12's snapshot under:

skills/herdr-teamlead/references/judge-round.md Step 13

Step 14 — Start the Judge Worker on Its Pinned Tier

An existing judge worker goes to Step 15. An empty shell pane starts under:

skills/herdr-teamlead/references/judge-round.md Step 14

CP=.tessl/plugins/gamussa/coding-policy; [ -d "$CP" ] || CP="$HOME/$CP"
bash "$CP/skills/herdr-teamlead/start-judge-worker.sh" \
  <step-13-plan-file> <pane> [claude|codex|grok] --task <task-id> \
  [--config <config-file>] [--state <state-file>]

Step 15 — Dispatch the Judge

Dispatch the judge with Step 8's apply under:

skills/herdr-teamlead/references/judge-round.md Step 15

Step 16 — Wait for the Ruling

Run Step 9's fleet observation loop, including the judge named by Step 13. Proceed immediately to Step 17 once its report lands; keep other enrollments under observation.

Step 17 — Act on the Ruling or Remedy

Route the ruling or remedy under:

skills/herdr-teamlead/references/judge-round.md Step 17

Step 18 — Release the Pull Request

Dispatch the release as a fresh release assignment and verify it. Read first:

skills/herdr-teamlead/references/round-completion.md Step 18

Step 19 — Clean Up the Worktree

Fast-forward the shared checkout, remove the worktree, and delete the branch per rules/agent-worktree-isolation.md, then run Step 6's prune script again for the round's other worktrees. Proceed immediately to Step 20.

Step 20 — Log the Round

Finalize the ledger, save progress and the lead's handoff, reconcile supervision, and report. Read first, then finish here:

skills/herdr-teamlead/references/round-completion.md Step 20

For the daily standup, use Skill(skill: "herdr-standup").