j-mauro-r/SAT-Dengue-V2 / .agents/skills/deepworkplan/addons/herdr
deepworkplan-addon-herdr
VerifiedOptional DeepWorkPlan addon that integrates herdr-peers (DailybotHQ/herdr-peers pinned at v1.0.0, protocol 1) as the interactive delegation transport - a thin integrator that detects the herdr-peers helper, offers it (never imposes it) from onboard Phase 7b, documents the pinned skill installs (herdr-peers and Herdr's official skill), records the acceptance in the .dwp/config.json addon registry, and maps a v7 plan's delegation operations onto one herdr-peers ask to a peer pane on any machine, with every delegation recorded in the plan journal. The message protocol lives in herdr-peers, never here. Never required, never a conformance gate.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.2 KB |
| SPEC.md | markdown | 7.9 KB |
| addon.json | config | 409 B |
| install.md | markdown | 3.6 KB |
| templates/INTEGRATION.md | markdown | 2.5 KB |
templates/INTEGRATION.md
View on GitHub# Template — one interactive delegate through herdr-peers (reason, don't copy-paste)
Fill every `<placeholder>` from the plan and the live Herdr listing; never
guess an address. Preconditions: `../../../execute/delegation.md` (v7
contract with `agent_delegation`, `parallel_safe` task or read-only
delegate, `addon:herdr` in the effective `subagents` sources) and
`HERDR_ENV=1` in this session.
## 1. Choose the peer
`herdr-peers list` (the helper's live listing). Prefer an idle agent; a
peer is `<machine_id>:<pane_id>` exactly as the listing prints it — labels
and row numbers are never addresses.
## 2. Compose the brief (data the peer reads)
- The task objective and its `AC-*` criteria, verbatim.
- For a writing peer: "work only in `<worktree>`" (pass `--worktree`).
- What to send back: a short summary of what changed and why.
- No secret values; no wider scope than the task.
`prompt_digest` = `sha256:` + the SHA-256 of exactly that brief.
## 3. Record, then ask
```bash
python3 <pack>/shared/ledger.py --plan <dir> delegate launch --task <T-id> \
--json '{"delegation_id": "<id>", "transport": "interactive", "via": "herdr",
"kind": "<kind>", "target": "<machine_id>:<pane_id>",
"worktree": "<path or null>", "prompt_digest": "sha256:<hex>"}'
DWP_PLAN=<dir> DWP_TASK=<T-id> herdr-peers ask [--worktree <path>] <machine_id>:<pane_id> "<brief>"
```
Keep the ask id the helper prints; note it next to `<id>`.
The brief names the peer's own pane and tells it to pass `--pane <pane_id>`
on its `herdr-peers` calls: a Codex peer runs its commands from a shared
per-profile server whose `HERDR_PANE_ID` names another pane, and without the
flag its reply is refused. When this session itself is a Codex lane, pass
`--pane` with its own pane on `ask`, `wait` and `check` too.
## 4. Observe and collect
- `ledger.py … delegate observe`; `herdr-peers check <ask-id>`.
- `herdr-peers wait <ask-id>` (or the reply lands in this pane). Save it to
`<dir>/analysis_results/delegations/<id>/reply.txt`.
- `ledger.py … delegate collect --task <T-id> --json '{"delegation_id":
"<id>", "state": "completed", "result_path":
"analysis_results/delegations/<id>/reply.txt"}'` (`failed` on a refusal
or timeout).
- Integrate the peer's worktree branch like any contribution, then run the
task's gates here through `ledger.py gate`.
## 5. Cancel
`herdr-peers cancel <ask-id> --reason "<why>"`, then `ledger.py …
delegate cancel --task <T-id> --json '{"delegation_id": "<id>"}'`.
Never answer the reply; never delegate from the peer; close only panes you
created.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |