Layout only, no behaviour and no wording. 161 hunks across 22 files, 98 of them
rustfmt joining a call or a message onto the one line it fits on. The config it
formats to, and how its four numbers were arrived at, is the commit before this
one.
Separate so that it is reviewable by not being read: nothing here is a decision,
and every decision is next door.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
A third asset on the machinery 16c2bed settled, so the wiring is one entry in
install::SKILLS.
Four jobs, priorities, due dates, tags and campaigns, with propose-then-apply
stated once at the top rather than per section. Every job writes to many
tickets at once and no field can be cleared back to unset, so the document
leans on the two traps that make a sweep destructive rather than merely
wrong: set --tags replaces the whole field, and a due date is neither
validated nor clearable.
feature-planner-agent.md is deliberately not folded in. It decomposes a
request into new tickets, which is intake; this orders the tickets that
already exist, and one document holding both would fit neither.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
install-skill now writes every document the binary carries, with an optional
name to narrow it. Requiring a name per document would mean a skill added
later never reaches anyone who already knows the invocation, which is the
drift the command exists to prevent. --print is the exception and requires
the name: a diff is against one document.
The review skill is its own document rather than a section of SKILL.md,
because the frontmatter description is the whole of what decides loading and
one description cannot name both "anything touching a ticket" and "only when
a review is asked for".
The reviewer never ticks a criterion and never moves the ticket. A tick is
the implementer's claim and unticking is the review disagreeing; one mark for
both loses the disagreement. mv belongs to whoever does the work.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
worklane's agent instructions only existed for someone with the repo checked
out. Anyone who installed the binary with cargo install got no document at
all, because cargo install places binaries and nothing else.
The skill now lives at assets/SKILL.md and is embedded with include_str, so an
installed copy can never be a different version from the binary that describes
it. `worklane install-skill` writes it, `--print` sends it to stdout so a
modified copy can be diffed, and a copy that was edited is reported and left
alone unless --force: it may have been changed on purpose, and silently
discarding that is worse than stopping.
One path serves both agents, ~/.claude/skills/worklane/SKILL.md. That was
settled empirically rather than from documentation: opencode 1.15.10 loads
~/.claude/skills as an external skill source alongside its own
~/.config/opencode/skill, and with HOME pointed at a temp directory holding
only what install-skill wrote, `opencode debug skill` lists the document under
the name worklane. Writing opencode's own path as well would be two copies of
one document, free to drift, for no gain.
The document is new rather than the one under .opencode, which is the user's
and not this repo's to ship. The ticket-workflow prose moved out of AGENTS.md
into it, so how to use worklane has one writer, and AGENTS.md points there.
The mechanism is in install.rs rather than skill.rs, and install() takes its
root as an argument: install-tool is coming, it needs a different root and the
same compare-and-refuse logic, and passing the root is what lets the tests
install into a temp directory instead of the home of whoever runs the suite.
Three tests guard the document itself, which is the part that goes stale
quietly: the frontmatter has to parse, every `worklane <x>` it shows has to be
a real subcommand, and every subcommand outside NOT_FOR_AGENTS has to appear in
it, so a new command cannot ship invisible to an agent.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>