Omar SobhandClaude Opus 5
5c2c63f8e8
Phase 4 of the plan, plus the PLAN_COMPLETE decision and the gitea_forge
cleanup from Phase 5.
THE REVIEW UI
mission_plan and mission_roster have been complete and reachable by curl
since they shipped, with zero frontend. That matters more than a missing
screen usually would: the decide step is not a convenience, it IS the
safety mechanism. Approving a plan replaces the mission's phases; approving
a roster flips it to the composed engine. A gate nobody can reach is a gate
that is always open or always shut.
MissionProposalDrawer, modelled on LevelUpDrawer which already does
load → review → decide. Reached from a mission's SETUP tab. Verified end to
end against the live backend, not just compiled: a model proposed a roster,
approval flipped the mission to `composed`, and approval on a non-draft
mission was refused.
The plan view shows each phase's done_when, and says plainly when one is
absent — a phase without a completion condition is never judged and reports
completed whatever it did, so its absence is the thing worth seeing.
AND THE DEFECT BUILDING IT FOUND
Every refusal path computed a precise reason — "the mission is running, not
a draft", "no node can boot that backend any more" — logged it to stderr,
and returned a bare {"error":"bad request"}. The person who needed the
sentence was the one clicking Approve; they got two words, and the reason
went to a server log they cannot read.
ApiError::Refused(String) carries it now. Same argument ApiError::Unavailable
was added for ("a 500 with 'internal error' sent them looking for a bug that
was not there"), one status code down. Live: the 400 now reads "this mission
is completed — a roster can only be approved while it is a draft, because
approving one rewrites how the mission will run".
PLAN_COMPLETE, decided
The Skill-Use measurement found that int-xx-marker-protocol documents
PLAN_COMPLETE and task_card_parser never implemented it, so an agent
following the skill exactly was silently ignored. Implemented rather than
removed from the skill: the planner needs a way to say it is done
specifying, and agents already emit it.
Marker ids are now strictly INT-<digits>. `starts_with("INT-")` accepted the
range form `INT-01..02` — observed live — which parsed into an id matching
no real item, so a task card appeared for something that did not exist while
the two items it covered stayed open. Rejecting is right: an ignored marker
is visible, a plausible row is not.
GITEA_FORGE, REMOVED
Named in nine places, defined in none. Harmless while provision_claw ignored
the bundle list; once the list was honoured, an undefined name became a
capability an agent is told it has and does not. Removed from seven team
templates, a workflow recipe, the auto-provision path, and a dropdown a user
could pick it from.
A new test asserts every bundle a template names is defined in the runtime
config — and it immediately found `web_fetch` in two templates I had missed
removing by hand. Same shape as the skill-binding test, one layer up.
Agents reach the forge through git over HTTPS with the ambient GITEA_TOKEN,
which is why nothing ever broke.
Full workspace suite green (106 binaries); frontend builds clean.
Co-Authored-By: Claude Opus 5 <[email protected]>
74 lines
2.3 KiB
TOML
74 lines
2.3 KiB
TOML
key = "frontend"
|
|
name = "Frontend"
|
|
description = "Latest React + TailwindCSS + ShadCN — component authoring, accessibility, responsive design."
|
|
stack = ["typescript", "react", "tailwindcss", "shadcn", "next"]
|
|
default_topology = "pipeline"
|
|
risk_profile = "coding_readwrite"
|
|
mcp_bundles = ["clawmates_door", "clawmates_skills"]
|
|
version = 1
|
|
|
|
[[roles]]
|
|
slot = "designer"
|
|
order_idx = 0
|
|
skills = ["decompose-int-items", "a11y-checklist"]
|
|
system_prompt = """
|
|
You are the DESIGNER of a Frontend team.
|
|
|
|
For each INT item: sketch the component's states, define props, list
|
|
edge cases (empty / loading / error / RTL / dark mode), and pick the
|
|
ShadCN primitives to compose. Hand off to the coder with the exact
|
|
Tailwind class names and any a11y notes.
|
|
"""
|
|
brain_seed = """
|
|
# Frontend design seed
|
|
|
|
## Every component gets four states
|
|
- empty (no data yet)
|
|
- loading (skeleton, never a spinner alone)
|
|
- error (with recovery affordance)
|
|
- ready
|
|
|
|
## Never author raw HTML for a primitive ShadCN ships.
|
|
"""
|
|
|
|
[[roles]]
|
|
slot = "coder"
|
|
order_idx = 1
|
|
skills = ["tailwind-v4-idioms", "workspace-repo-commit-protocol", "int-xx-marker-protocol", "component-4-state-model", "react-19-server-components"]
|
|
system_prompt = """
|
|
You are the CODER of a Frontend team.
|
|
|
|
Working directory /workspace/repo. Implement per the DESIGNER's spec.
|
|
Type strictness > convenience — no `any`, no `as` escapes without a
|
|
comment explaining why.
|
|
"""
|
|
brain_seed = """
|
|
# React/TS memory seed
|
|
- Server components by default; 'use client' only where interactivity
|
|
or hooks demand it.
|
|
- Tailwind class order: layout → box → typography → color → state.
|
|
- No inline styles on components that render more than once.
|
|
"""
|
|
|
|
[[roles]]
|
|
slot = "tester"
|
|
order_idx = 2
|
|
skills = ["playwright-e2e-patterns", "a11y-checklist", "tdd-red-green-refactor"]
|
|
system_prompt = """
|
|
You are the TESTER of a Frontend team.
|
|
|
|
Unit tests with Vitest for pure components. Playwright for flows.
|
|
Axe scan every page under test — a11y regressions fail the build.
|
|
"""
|
|
brain_seed = ""
|
|
|
|
[[roles]]
|
|
slot = "committer"
|
|
order_idx = 3
|
|
skills = ["workspace-repo-commit-protocol", "small-focused-commits"]
|
|
system_prompt = """
|
|
You are the COMMITTER. Only run on green tests + a11y pass. Emit
|
|
COMPLETED: INT-<NN>.
|
|
"""
|
|
brain_seed = ""
|