build
Apply a specced work item the way a flywheel build construction session does — /opsx:apply on a nested construction worktree, several items per session…
Skill by agentplot
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/agentplot-build
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/build
What's inside
- Skill name
build- Description
- Apply a specced work item the way a flywheel build construction session does — /opsx:apply on a nested construction worktree, several items per session, neighbours re-read from disk before claims are trusted. Use whenever a construction session's work order names the build type.
- License
- MIT
- Instructions
- 56 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Flywheel build — applying the spec You are a construction session charged with the **build type**. Your batch holds work items that are specced and reviewed per the bolt type; your output is the applied change, committed on your branch. ## The mechanics In your worktree — `build/<slug>`, cut off the bolt branch — in the built repo, run `/opsx:apply` with the change id. Work the batch to done, commenting each item as it completes. A small fix adjacent to your batch's released scope is work — make it, commit it, note it in your report; anything beyond is a queued item, filed in a minute. ## Re-read the neighbours before trusting the spec Before building on any claim the spec makes about a neighbouring artifact's state — a decision record, a sibling change, a file's current shape — re-read that neighbour from disk. Build time is when the neighbours have had longest to move; the spec's snapshot is a starting point, not a warranty. ## Verify on disk before reporting done Done is a state of the tree, not of the transcript. Before reporting, run what the repo's gates and the change's tasks name — build, tests, checks — and separate in your report what you verified on disk from what you are relaying. A task you could not verify is reported as unverified, never rounded up to done. ## You build; you do not merge Your branch is merged back to the bolt branch by the loop, through the gate, once you settle. You never merge your own branch or write the bolt branch or main directly. Book chapters and the context map are the design loop's — a change that would edit them is a design finding, queued, and the andon cord if the batch depends on it. ## On the tracker The object-graph rules are the shared copy at `skills/_reference/tracker.md`; the invocations are in `herdr.md` beside it. Your contract: - **You receive**: specced work items, reviewed per the bolt type, on a nested construction worktree. - **You leave**: the applied change committed on your branch by pathspec, and a "build done" comment per item. The loop merges through the gate and closes; you never land or close. - **Commit messages follow the built repo's own conventions** — its AGENTS.md or CLAUDE.md Commits section, with a `Refs: #<item>` footer. Never invent a format, and never use a loop stage name (`spec:`, `build:`) as a commit type. - A finding beyond your spec is a queued item, never an in-place fix. ## What you report What was applied and verified per item, the commits on your branch, anything unverified or stopped on, and what the next batch should work.
From agentplot/flywheel, MIT.
More from agentplot/flywheel
- 0.524score
interactive
agentplot
Build the lavish page a flywheel interactive-design session works — one artifact carrying every decision the batch aims to close, with options, trade-offs…
SkillBFreshness: BClaude Code +9 - 0.524score
bolt-planning
agentplot
Run a bolt planning session — read a system's design book, the built repo's implemented specs, and the changes in flight; carve the remaining gap into one or…
SkillBFreshness: BClaude Code +9 - 0.524score
construction
agentplot
Run the flywheel construction loop — the bolt loop drives an approved plan's work items through spec, build, verify, merge and landing across built-repo bolt…
SkillBFreshness: BClaude Code +9 - 0.524score
findings-routing
agentplot
Author the dispatch-plan payload a flywheel findings-routing session builds over a bolt's queued findings — the whole findings inbox seeded for one operator…
SkillBFreshness: BClaude Code +9 - 0.524score
fleet
agentplot
Drive an org's flywheel fleet from its manifest — flywheel up starts the server that runs the loops, flywheel dispatch starts the org's standing dispatch…
SkillBFreshness: BClaude Code +9 - 0.524score
import
agentplot
Run the messy-repo import a flywheel import-charged design session works — inventory a corpus of planning docs, cut it against the destination books, convert…
SkillBFreshness: BClaude Code +9 - 0.524score
inception
agentplot
Run the flywheel design loop — dispatch raw ideas into intent changes and tracker items, run design sessions that close decisions and write the books and the…
SkillBFreshness: BClaude Code +9 - 0.521score
human-code-review
agentplot
Run the operator's review round a flywheel human-code-review construction session prepares — built diffs put in front of the operator through plannotator, the…
SkillBFreshness: BClaude Code +9 - 0.521score
code-review
agentplot
Run the read a flywheel code-review construction session takes over built work — adversarial against the spec and its cited decisions, or through a persona…
SkillBFreshness: BClaude Code +9 - 0.316score
openspec-archive-change
openspec
Archive a completed change in the experimental workflow.
SkillBFreshness: BClaude Code +9 - 0.316score
openspec-explore
openspec
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements.
SkillBFreshness: BClaude Code +9 - 0.316score
openspec-propose
openspec
Propose a new change with all artifacts generated in one step.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 38
- Last commit (this folder)
- Aug 18, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/agentplot/flywheel
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from agentplot
- 0.524score
interactive
agentplot
Build the lavish page a flywheel interactive-design session works — one artifact carrying every decision the batch aims to close, with options, trade-offs…
SkillBFreshness: BClaude Code +9 - 0.524score
inception
agentplot
Run the flywheel design loop — dispatch raw ideas into intent changes and tracker items, run design sessions that close decisions and write the books and the…
SkillBFreshness: BClaude Code +9 - 0.524score
bolt-planning
agentplot
Run a bolt planning session — read a system's design book, the built repo's implemented specs, and the changes in flight; carve the remaining gap into one or…
SkillBFreshness: BClaude Code +9 - 0.524score
construction
agentplot
Run the flywheel construction loop — the bolt loop drives an approved plan's work items through spec, build, verify, merge and landing across built-repo bolt…
SkillBFreshness: BClaude Code +9 - 0.524score
findings-routing
agentplot
Author the dispatch-plan payload a flywheel findings-routing session builds over a bolt's queued findings — the whole findings inbox seeded for one operator…
SkillBFreshness: BClaude Code +9 - 0.524score
fleet
agentplot
Drive an org's flywheel fleet from its manifest — flywheel up starts the server that runs the loops, flywheel dispatch starts the org's standing dispatch…
SkillBFreshness: BClaude Code +9
Cite this page
build skill. Agent Mart. https://agentmart.dev/skills/agentplot-build (last updated 2026-10-24)