Skip to content
Agentmart
Submit a tool

st-build

Full-lane Build phase.

Skill by HyuseCS

IndexedMIT★ 3
Write a review

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/hyusecs-st-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.

We use your email only for this newsletter. Privacy

About

Full-lane Build phase. Run the build loop over tasks.md - test first, build, verify, commit per task; debug after 2 failed tries; review each story.

Use cases: testing, productivity

No 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 and code. Checked Oct 26, 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/st-build

What's inside

Skill name
st-build
Description
Full-lane Build phase. Run the build loop over tasks.md - test first, build, verify, commit per task; debug after 2 failed tries; review each story.
License
MIT
Instructions
78 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# /stratum:st-build

You are the orchestrator. You route and verify; subagents write the code.
Plugin root (`<plugin root>`) is two levels up from this skill's base directory. Pass every
subagent absolute paths: plugin root, project root, feature dir, and its task IDs.

## 0. Start

1. Read `<project>/.stratum/state.json`. If there is no `feature_directory`, stop and tell the
   user to run `/stratum:st-define`.
2. Read `<feature>/tasks.md`. Work on unticked tasks in order, phase by phase.

## Per task

1. A test task goes to the `st-test` agent (`stratum:st-test`). It writes the test and shows it fails.
   Check the failing output yourself. A test that passes before the build is wrong.
2. The build tasks that follow go to the `st-build` agent (`stratum:st-build`). It builds until that test
   passes and ticks the task `[X]` in tasks.md. Setup tasks with no test go straight to `st-build`.
3. **Verify.** From the project root, run
   `bash <plugin root>/scripts/st-verify.sh '<test command>' <files the task touched>`.
   It re-runs the test, greps the diff for added comment lines, and prints one line. Send any
   `FAIL` back to `st-build`.
4. **Two tries.** If the test is still red after 2 `st-build` tries, run the advisor (see Advisor): save the task text and both failure outputs to files in your scratchpad, then run
   `bash <plugin root>/scripts/st-advisor.sh test <feature dir> <task file> <test path> <failure 1 file> <failure 2 file>`: root cause or rabbit hole?
   For a `[P]` task in a worktree, run it in the main session after the subagent reports both failures, with the working directory at that worktree's root and `<feature dir>` as the main checkout's absolute path, so the record lands in the main checkout. Start `st-debug` from the main session too, with the worktree path; it diagnoses, fixes and verifies in that worktree.
   Then start the `st-debug` agent (`stratum:st-debug`) with the task, the test, both failure outputs, and the advisor's answer.
5. **Commit.** The `st-git` agent (`stratum:st-git`) commits the exact paths of the task, with tasks.md, and `<feature dir>/advisor.md` if it changed.

## Parallel tasks `[P]`

When the project is this session's own repo, run each `[P]` task of a phase in its own subagent
with `isolation: "worktree"`, all started in one message.
Each runs the per-task steps in its worktree, except step 4: a subagent whose test is still red after 2 tries stops and reports both failures.
Then check each branch (tests green, no added comments) and merge it into `main`
yourself. Keep each worktree and branch after the merge. Delete one only when the user says so.
Never delete a remote branch: the user does that. If the project is another repo, run `[P]` tasks one after another.

## Per story (after its last task)

1. The `stratum:st-review` agent on the story's diff.
2. For screen work, run the `st-impeccable` skill on the changed screens.
3. Check each finding against the source first (see `/stratum:st`). Send the real, small ones to
   `st-build`; verify and commit them like a task. Big ones go to the user. Drop the false ones.
4. Run the story's steps from `<feature>/quickstart.md`. Give the user exact steps for any
   step you cannot run.

## Stop only when

- A subagent is blocked, or a big decision falls outside the plan (see `/stratum:st`). Bring it
  to the user, one question at a time, with your recommendation. Decide small ones yourself.
- Work touches a higher impact area than the lane allows: move up a lane.

When all tasks are ticked, consult the advisor if one is set (`/advisor`) on the feature's full
diff: hidden regressions, broken rules from the constitution. Handle its notes like review
findings. Then say so, list the small decisions and findings (fixed and dropped), and name the
next phase: `/stratum:st-close`.

## Advisor

The advisor is Codex (the `codex` CLI), a model from another vendor. It runs at two points: the plan before the Plan gate (`st-plan` step 4, stale-checked at the build gate by `st-inspect`) and a test still red after 2 tries. The full diff before the build is called done and every Fast-lane point use `/advisor`. The Quick lane has no advisor.

- Run `bash <plugin root>/scripts/st-advisor.sh <point> ...` from the project root in the foreground, with a Bash timeout of 600000 ms, and wait for it. No background run, no polling.
- Codex only reviews, in the read-only sandbox. Never run `codex` to build or fix.
- `no advisor: codex not found`, `no advisor: mode not set` (show the user its line) or `no advisor: mode off`: go on as before; consult `/advisor` only if the user set one.
- First line `mode both: also consult /advisor if one is set`: after Codex, consult `/advisor` on the same input if one is set.
- `APPROVED`: go on.
- `REVISE`: handle each finding like a review finding: check it against the source, fix the real small ones, bring big ones to the user, drop the false ones. Then run the same point once more on the changed input. Two rounds at most per point per gate pass, then the user decides. A later gate pass starts a new count.
- `BLOCKED: <reason>`: stop and show the user the reason. Nothing passes the gate. If the user says to continue, run `bash <plugin root>/scripts/st-advisor.sh continued <point> <feature dir>` and skip the point. Do not retry it in this gate pass.
- Each run appends a record to `<feature dir>/advisor.md`: the point, the time, the SHA256 of the input, the verdict and the findings. The mode comes from `.stratum/advisor.json` (`codex`, `both` or `off`). No file means off, with the `mode not set` line.
- At the build gate, `check plan` compares the latest plan record with the current input. `advisor approval is stale` or `no record` counts as no approval: run the plan point once more, as a round. Skip the check after a `no advisor` line.
- Exit 2 with a `usage:` line or `cannot hash inputs`: the script could not read or hash its inputs. Nothing was recorded and nothing was sent. Fix the input or the tool and run the point again.

## Always

- Never skip the commit guard. If a commit is blocked, tell the user; do not work around it.
- Push only when the user says "push".

From HyuseCS/stratum, MIT.

More from HyuseCS/stratum

Signals

Stars
3
Forks
0
Open issues
4
Last commit (this folder)
Oct 23, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from HyuseCS

Cite this page

st-build skill. Agent Mart. https://agentmart.dev/skills/hyusecs-st-build (last updated 2026-10-24)