orchestrate-herdr
Dispatch spec (PRD) sub-issues to worker tabs; monitor to done. Tab, CLI, or runtime context selects herdr; without any of these: /ask-kit. Tab status or actions with no dispatch: herdr companion.
How do I install this agent skill?
npx skills add https://github.com/devarfeen/agent-skills-kit --skill orchestrate-herdrIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill orchestrates multi-agent workflows by fanning out tasks from trackers (GitHub/Linear) to worker agents via the herdr CLI. It is primarily a management tool that coordinates terminal sessions and prompts. The security profile is generally safe, with the main consideration being the indirect prompt injection surface created when external issue tracker data is passed into sub-agent prompts. It includes specific guidelines to prevent the exfiltration of secrets like environment files.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 1 issue
What does this agent skill do?
Orchestrate herdr
Fan work out to one herdr-managed worker tab per unit (tracker sub-issue or harness prompt) and drive each to a test-backed end state when the task involves code. You are the orchestrator: never implement, never close your own tab.
Inputs
Run mode — spec when SPEC_REF is present; otherwise harness per references/harness.md. Never guess an input.
- SPEC_REF (spec mode) — parent issue whose open sub-issues become workers: Linear
PRWL-100/ABC-123, or a GitHub issue URL or number. From skill args (SPEC_REF=..., bare reference; legacySPEC_URL=/PRD_URL=accepted) or intake. - WORKERS (harness mode) — list of
{label, prompt}; defined per harness reference. - AGENT — worker runtime. Its
CLI_NAMElaunch token serves PATH checks/tab labels;AGENT_KINDserves herdr--kind. Both come fromreferences/intake.md, never the command's first token: Cursor's values differ. - CODING_CLI —
CLI_NAMEplus the permission-mode flags from the user's established preference or intake choice. The prompt is never a launch argument (see Rules). - ISOLATION —
worktree,branch, orshared; it decides whether workers can run in parallel. - TRACKER / TRACKER_TAG — workspace tracker of record (
G/L). Derived per Resolve inreferences/tracker-map.md, which holds the per-tracker commands cited by bold section name below.
Factory stage. Under a user-started /factory run on herdr, follow references/factory-stage.md instead of Intake.
Rules
-
Zero attribution. Omit co-author, AI, and tool attribution from prompts, commits, tracker comments, and reports.
-
Never implement. The orchestrator reads, creates tabs, submits prompts, monitors, and reports — nothing else.
-
Herdr-managed tabs only, created in the existing herdr workspace/session. No pane splits, no internal sub-agents, no nested coding sessions, and never launch
CODING_CLIfrom inside anotherCODING_CLI. -
Isolation is the user's choice, and herdr's job. Keep the orchestrator's working directory. Create worktrees only in selected
worktreemode throughherdr worktree create, never hand-rolled Git. Verify project-owned placement per Intake before launch; unsupported placement blocks that worker.branchandsharedtabs start in the orchestrator's folder, which must be the assigned repository's checkout. -
Saved IDs only. Every submit, read, monitor, and follow-up call uses a tab ID and agent name saved at creation — never the active tab, latest tab, visual order, or a guess.
-
Prompts are pasted and submitted into a ready CLI — never passed as launch arguments/flags, never left staged or unsent, and never pasted into a dead tab's shell, where the prompt text would execute as commands.
-
Read completion evidence from the tab. A task whose diff touches source or tests requires the test command and quoted passing output, however the worker describes it; a non-code task requires the evidence its prompt named, or the observable result when none was named. Spec tasks also require an
AC map:covering every criterion. Missing proof stays incomplete; a summary alone is a claim. -
Suggest, never auto-chain. After the final report, suggest
/agentic-qafor each PR whoseAC mapowes rows to it,/code-reviewon the workers' diffs, or/release-notesfor what shipped — suggest only, then stop.
Workflow
Emit Stage / Found / Next / Needs user at each phase transition — one line per field. Transitions: tabs created, prompts submitted, any worker status change, final report.
1. Pre-flight
Fail fast before creating anything, naming what is missing:
HERDR_ENV=1is set — you are inside herdr. Not set → stop.- Load the herdr companion per Companion in
references/herdr-commands.mdunless already in context — it ships inside the binary, so this is a load, not a gate. That file holds the herdr commands cited by bold section name below. - Mode:
SPEC_REFpresent → spec; noSPEC_REF→ harness. When the run uses tracker APIs (spec mode, or harness workers with issues), resolveTRACKER/TRACKER_TAGper Resolve and run that tracker's access check. - Harness-only: empty WORKERS after define step → stop.
2. Build the worker set
Spec — list open sub-issues per Discover. State the count and cross-check against the spec before tabs — under-fanning drops slices. Every open sub-issue; ready-for-agent does not filter. Identifier <n> per issue. Zero open → stop before Intake. A sub-issue blocked by another open sub-issue is not parallel work; list pairs per Discover and ask in Intake question 3.
Harness — define WORKERS per references/harness.md. State the count before tabs.
3. Intake
Ask one batched question set, after Discover and never before — two of the four need the issue list. Name the affected issues and repos in the questions. Away-fallbacks and the full matrices: references/intake.md.
- Which coding agent. Offer all six runtimes by product name per Intake roster; parenthesised token is
AGENT_KIND. Never label an option with a bare binary. Offer every runtime whose launch token is on PATH and say which are missing. - Which permission mode. Reuse the user's established permission mode; otherwise offer the verified interactive preset or bare launch token per Intake. The selected mode becomes
CODING_CLI. - How work is isolated.
worktree,branch, orshared; recommendworktreewhenever two open sub-issues share a repo. - Leftover tabs and agents from a previous run of this spec — monitor them, or create alongside.
4. Create worker tabs
Save the caller's workspace, tab, and folder per Context. One tab per worker: spec → [CLI_NAME] - <TRACKER_TAG> #<n>; harness → [CLI_NAME] - <label>. ISOLATION picks Creating worktrees or Create tab. Save each worker's context, tab/pane IDs, agent name, and verified checkout record per checkout binding. An unresolved repository or wrong native placement blocks launch.
5. Launch workers
Parallelize the slow parts across tabs:
- Start every worker per Start agent,
AGENT_KINDas--kindandCODING_CLI's flags after--. Each call blocks until its agent is ready, so issue them concurrently.branchisolation on a shared checkout is the exception: dispatch those workers one at a time. Never poll or sleep for readiness.agent_not_readymeans it booted straight into an approval UI — surface that under Needs user, never relaunch it; any other error is a dead-CLI case under Monitor. - Submit that issue's worker prompt per Submit.
A worker is not launched until its tab ID and agent name are saved, its prompt is accepted, and its first response is visible.
Spec: fill references/worker-prompt.md, one issue per worker. Harness: append its footer and checkout binding to that worker's prompt. Pass applicable instructions and the saved checkout record; workers verify identity and baseline before edits. Local lanes when useful; never cloud.
Code workers without /tdd-loop still owe test evidence; say so in the launch update.
6. Monitor
Wait on lifecycle state per Watch — it reacts the moment a worker settles, and needs no sweep. Read a settled tab per Read. After compaction or restart, recover per Context before any call.
- States:
blocked→ an approval or question UI; surface under Needs user, never relaunch or answer it.idle/done→ read the tab for the report.working→ leave it. - Stalls:
unknownnever proves completion. After a start, submit, or wait error, inspect state and output before retrying; a timeout can follow successful submission. Agent gone → redo Launch workers once after confirming its process exited. A live long test stays running; silence alone never makes it blocked. Report a blocker only with an observed failure or missing human decision. - Labels: human blocker on a tracker-assigned worker →
ready-for-humanand a decision comment per Block. Never edit issue titles (noBLOCKER:,AFK:, orHITL:markers). - Completion: read each tab per Read; quote passing test output for code tasks, assigned evidence for non-code tasks.
- Status board: on every state-change wake, emit a one-line count —
N running · M completed · K blocked/needs-user— naming any tab whose state changed.
7. Report
Report mode, agent, isolation, workspace/session ID, folder, tab map and assignments, each end state, task evidence, and AC map / Decisions / Open items (AC map in spec mode). In worktree/branch mode, list files changed by multiple branches (git diff --name-only <base>...<branch>) as merge risk.
Completion criteria
- The final tab map accounts for every worker in the set (discovered sub-issues or harness WORKERS), including failed launches and exited workers; saved IDs and end states match read-back
- Each tab, read back, shows its submitted prompt and a worker response — nothing staged or unsent
- Each launched worker's checkout and instructions match its prompt; write tasks report baseline and first-write identity
- In
worktreeorbranchmode, each worker's commits land on that issue's branch and no other - Every worker is completed with code-test or assigned non-code evidence (plus spec
AC map), blocked, or errored - Each blocked tracker-assigned issue shows
ready-for-humanand a decision-naming comment in the Verify read-back, title unchanged - The transcript ends with the final report and the
/agentic-qa//code-review//release-notessuggestion — nothing after it
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/devarfeen/agent-skills-kit/orchestrate-herdr">View orchestrate-herdr on skillZs</a>