Solve task - this repo's own flow
One change to alfred-code, from the request to a local commit, through the superpowers skills and this repo's
invariants (CLAUDE.md). Each step that names a skill loads it with the Skill tool.
When to use
- A change to this repo that is more than one sentence: a feature, a fix, a hook, a skill, an installer step.
- Not for a consuming project, which runs the stack's
task-solve; not for a release, which has its own procedure.
Size first
State one line before anything else: Size: <trivial|spike|bounded|architectural> - <the signal>.
- trivial - no behaviour a test would see: a typo, a comment, formatting, a rename inside one file. It just gets
made (
.claude/rules/execution.md), its covering check runs, done. Anything that adds or changes behaviour - a new
flag, option, output or branch - is at least bounded, however short the request.
- spike, bounded, architectural - load superpowers:brainstorming next and take its path for this size: a spike has its question
and probe approved first, then ends in an answer and keeps nothing; a bounded change gets an in-chat design whose approval is a stop, then the build; an
architectural change takes every step below. Under
auto-run a bounded design's approval follows the same rule
and waiver as a graded spec's (step 3).
- A design already settled by a run order or the user's rulings skips the spec and goes to the plan.
The steps
Spec - superpowers:brainstorming writes docs/superpowers/specs/<date>-<topic>-design.md.
Grade - refining-plans to 90, its own loop.
Approval - the user approves the graded spec. Under auto-run it stays a stop; only the waiver auto-run
defines skips it, and then the score path is reported in place of the ask.
Plan - superpowers:writing-plans writes docs/superpowers/plans/<date>-<topic>.md; grade it to 90; approval as in
step 3.
Build - superpowers:executing-plans by default (one context, cheapest), superpowers:subagent-driven-development
when the user asks for a gate per task, or when all of execution.md's Mode conditions hold; with
superpowers:test-driven-development throughout. The ledger is docs/superpowers/sdd/<plan basename>/progress.md.
Checks, in the tiers of execution.md:
- per batch:
npm run lint and the tests that cover the change;
- a temp-project matrix from this working tree with CLAUDE.md's required edge cases - fresh install, update over
an older install, re-run, the user's own config kept, missing or garbage input, every scope, every boundary -
reading the written files, never the exit code alone;
- the full
npm test once, in the background, its output to a log, its tail read.
House voice holds in every file written (single dashes; lint check 32). A case not run is reported NOT RUN.
Review - one fresh Opus review of the whole branch, one fix pass (each fix RED then GREEN), minors deferred to
the ledger.
Commit - one commit per plan task as its commit step says, else one commit for the change; by pathspec, never
.gitignore or docs/habits-scorer-flow.html. No version bump, push or merge without the user's word.
The close
execution.md's close - the mode and why, what changed, each tier's command with its result, what was not verified
and why - then 'Rulings I made' and 'Deferred minors' from the ledger, and auto-run's close when it is on.
Not here
- The Cursor mirror (paused since 2026-09-23).
- The stack's own
task-solve and its seats, stamps and stops.
1---2name: solve-task3description: "Use when solving a task in this repo end to end - '/solve-task', 'solve this', 'spec, plan and build it'. This repo's own flow, not the stack's task-solve."4metadata:5 source: https://skillmd.com/skills/envoydev/solve-task6---78# Solve task - this repo's own flow910One change to alfred-code, from the request to a local commit, through the superpowers skills and this repo's11invariants (`CLAUDE.md`). Each step that names a skill loads it with the Skill tool.1213## When to use1415- A change to this repo that is more than one sentence: a feature, a fix, a hook, a skill, an installer step.16- Not for a consuming project, which runs the stack's `task-solve`; not for a release, which has its own procedure.1718## Size first1920State one line before anything else: `Size: <trivial|spike|bounded|architectural> - <the signal>`.2122- trivial - no behaviour a test would see: a typo, a comment, formatting, a rename inside one file. It just gets23 made (`.claude/rules/execution.md`), its covering check runs, done. Anything that adds or changes behaviour - a new24 flag, option, output or branch - is at least bounded, however short the request.25- spike, bounded, architectural - load superpowers:brainstorming next and take its path for this size: a spike has its question26 and probe approved first, then ends in an answer and keeps nothing; a bounded change gets an in-chat design whose approval is a stop, then the build; an27 architectural change takes every step below. Under `auto-run` a bounded design's approval follows the same rule28 and waiver as a graded spec's (step 3).29- A design already settled by a run order or the user's rulings skips the spec and goes to the plan.3031## The steps32331. Spec - superpowers:brainstorming writes `docs/superpowers/specs/<date>-<topic>-design.md`.342. Grade - `refining-plans` to 90, its own loop.353. Approval - the user approves the graded spec. Under `auto-run` it stays a stop; only the waiver `auto-run`36 defines skips it, and then the score path is reported in place of the ask.374. Plan - superpowers:writing-plans writes `docs/superpowers/plans/<date>-<topic>.md`; grade it to 90; approval as in38 step 3.395. Build - superpowers:executing-plans by default (one context, cheapest), superpowers:subagent-driven-development40 when the user asks for a gate per task, or when all of `execution.md`'s Mode conditions hold; with41 superpowers:test-driven-development throughout. The ledger is `docs/superpowers/sdd/<plan basename>/progress.md`.426. Checks, in the tiers of `execution.md`:43 - per batch: `npm run lint` and the tests that cover the change;44 - a temp-project matrix from this working tree with CLAUDE.md's required edge cases - fresh install, update over45 an older install, re-run, the user's own config kept, missing or garbage input, every scope, every boundary -46 reading the written files, never the exit code alone;47 - the full `npm test` once, in the background, its output to a log, its tail read.4849 House voice holds in every file written (single dashes; lint check 32). A case not run is reported NOT RUN.507. Review - one fresh Opus review of the whole branch, one fix pass (each fix RED then GREEN), minors deferred to51 the ledger.528. Commit - one commit per plan task as its commit step says, else one commit for the change; by pathspec, never53 `.gitignore` or `docs/habits-scorer-flow.html`. No version bump, push or merge without the user's word.5455## The close5657`execution.md`'s close - the mode and why, what changed, each tier's command with its result, what was not verified58and why - then 'Rulings I made' and 'Deferred minors' from the ledger, and `auto-run`'s close when it is on.5960## Not here6162- The Cursor mirror (paused since 2026-09-23).63- The stack's own `task-solve` and its seats, stamps and stops.