Rewrite SKILL.md to state the stance (reconnoitre, then route all work through Pipelines runs; manage and debug, never implement), keep the existing authoring/operations index, and route to four new references. Add references/orchestration.md (stance, work items, brief template, hard constraints, pipeline choice, running and watching), references/lanes.md (worktrees, devices, sync/merge, restart-replay cursor fix), references/debugging.md (eight symptom/confirm/do playbooks) and references/delivery.md (artifacts, LAN URLs, WIP naming, install boundaries), each with a clearly labelled project example where Android/device specifics apply. Append orchestration verification habits to references/verification.md and add the four new files to install.go's managed inventory.
7.6 KiB
Orchestrate work through runs
When the operator asks for a change to this project, the agent's product is a set of briefs and a set of managed runs, not the change itself. The implementer stage makes the change; the reviewer stages check it; the committer stage commits it. Route all project work through Pipelines runs.
Stance
- Reconnoitre first. Read enough of the repository, its notes and recent history to write a truthful brief: name the exact files, functions, commands and existing helpers the change touches. Do not guess and do not hand-roll the change to avoid reading.
- Then route every work item through a run. Do not edit the project's files yourself, not even a one-line unblock. A hand edit has no brief, no independent review and no recorded run, so nothing about it can be reviewed or trusted.
- Fix the cause, not the symptom. When a run wedges, fix the pipeline definition,
the stage configuration or the Pipelines/harness service. Do not reach around a
stuck stage and finish its work by hand. Diagnose with
references/debugging.md. - The agent decides scope, decomposition, pipeline choice and what to publish; the operator owns the decisions a run cannot make — which items to accept, what to publish, when to restart a service, when to install on real hardware. Ask only for those.
Work items
Decompose the request into single-purpose items, roughly an hour of agent work each.
- One item is one coherent change with its own brief, its own evidence and its own review, so the operator can review it on its own.
- One item = one run = one commit (the committer stage commits). Do not batch unrelated changes into one run; a run whose reviewer is arguing about two independent changes is unreviewable.
- State dependencies and ordering: which items must land first and which are
independent. Independent items may go to parallel lanes
(
references/lanes.md); dependent items run in order. - Prefer more, smaller items to fewer large ones: a smaller item is cheaper to review, cheaper to retry, and less likely to loop back through the reviewer.
The brief
A brief is the entire task a run receives. The run does not see this conversation, the operator's intent beyond the brief's words, or any context that is not on disk. Write it self-contained.
Every brief has:
- Goal — one line naming the change.
- The observed problem — what is wrong today and why it matters, in the repository's own terms, naming the exact files, commands or runs.
- Requirements — a short bulleted list of the exact behaviour, the surfaces it touches, and every constraint the change must honour.
- Falsifiable evidence required — the exact commands the run must run and the output it must report, plus the screenshots the reviewer must read. Say plainly: "report the exact commands and their observed results. Do not claim a check you did not run."
- The hard constraints block (below).
- Publishing rules (
references/delivery.md).
Template:
<one-line goal: the change, in the repository's own words.>
<what is wrong today and why it matters; name the exact files, commands or runs.>
- <requirement 1: the behaviour and the surface it touches>
- <requirement 2>
...
Evidence: <exact build/test commands> and <the screenshots or captures asked for>;
report the exact commands and their observed results. Do not claim a check you did
not run.
Constraints: <scope: the one subtree or package this item may touch>; no new
dependencies; do not restart, rebuild or reconfigure the Pipelines or OpenCode
server, the installer, the ntfy service or any other service - runs and lanes are
active; never install on the operator's physical device; keep geometry and values
from their single existing sources rather than new literals; commit locally only,
never push; <the item's publishing rules>.
Requirements must be concrete and checkable. Name files, functions, commands, and the existing helpers to reuse. State what must survive — existing behaviour, other lanes' work. If a requirement cannot be checked by a command or by an image a reviewer can open, it is not evidence: rewrite it.
Do not write a brief that asks a stage to do a vague job ("make the UI better"). A reviewer cannot falsify it and the run will drift. One item, one observable outcome.
Hard constraints to carry into every brief
Adapt the scope and publishing lines per item; keep the rest.
- Scope — the single subtree or package the item may touch, and nothing else.
- No new dependencies unless the brief argues the exception in-line.
- Do not restart, rebuild or reconfigure the Pipelines server, the CLI, the installer, the OpenCode service or ntfy, and do not touch another lane's worktree or device.
- Never install on the operator's physical device — only the lane's own emulator
or device (
references/lanes.md). - Keep values from single sources — geometry, tokens, sizes and constants come from the source that already owns them, not from new literals.
- Commit locally only, never push — the committer stage commits, no other stage.
- Publish rules — WIP artefact naming and LAN URLs per
references/delivery.md.
Pipeline choice
- Use a pipeline that keeps implementer + reviewer + ui_reviewer + committer for anything that matters. The planner is the only stage a leaner variant may drop.
- Never remove a review stage to go faster. The reviewer stages are the independent evidence the operator reviews against; dropping them is exactly how a regression ships unreviewed.
- The
ui_reviewermust build, capture and read the actual screenshots, or returnskippedwith a reason when the change has no rendered surface. Never accept a UI change approved without the images. - The committer is the only stage that commits, and it stages only the run's changed files.
- Choose per item: a logic, server or format change usually wants the planner (a plan/implement/review pipeline); a small, fully understood tweak may use the leaner implementer-first variant. Both keep all review stages.
Running and watching
- Launch with the authoritative
CLI_PREFIX(pipelines run). The brief text is the run's task; pass it whole. Readreferences/operations.mdfor the exact flags —--json, confirmation (--yes) and--wait/--wait-timeout. - Watch to a terminal state (
succeeded,failed,canceled,interrupted). PollCLI_PREFIX inspect RUN_ID --json(or use--wait) until terminal. A reached client wait limit is not a run failure: the run stays active; keep waiting or reattach with the original request key, never start a duplicate run. - Read the outcomes, not just the status: the option each stage returned, the
evidence it recorded, and any run or step diagnostic. Interpret diagnostics by
category (
references/debugging.md). - Retry once, then record and continue. Retry a failed or interrupted item at most once. If it fails again, record the brief as failed and move to the next item; never loop or start duplicates to force a pass.
- Stop the chain on failure and verify by hand. Do not push the next item on top of a broken tree. Inspect the failure, fix the pipeline or service cause, and verify the tree by hand before continuing. Report the failure; never hide it by re-running until something passes.
What the operator reviews
From the run record alone, the operator must be able to see: the brief, the changed
files and diff, the reviewer's exact commands and observed results, the screenshots
the visual reviewer read, and the commit. Produce those, and say plainly what was
not tested (references/verification.md).