Skip to content
Agentmart
Submit a tool

build

Use when writing or changing code - features, bug fixes, refactors - starting feature work in a fresh isolated worktree with a clean baseline, or executing an…

Skill by Srimukh99

IndexedMIT
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/srimukh99-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

Use when writing or changing code - features, bug fixes, refactors - starting feature work in a fresh isolated worktree with a clean baseline, or executing an approved plan task by task with check-ins after each batch. Test-first loop, tiered checks, and a guard against skipped or weakened tests.

Use cases: testing, writing, productivity

Reviews

Write a review

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. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

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
Use when writing or changing code - features, bug fixes, refactors - starting feature work in a fresh isolated worktree with a clean baseline, or executing an approved plan task by task with check-ins after each batch. Test-first loop, tiered checks, and a guard against skipped or weakened tests.
License
MIT
Instructions
15 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (7)

  • SKILL.md
  • build.md · references/
  • prove-it.md · references/
  • sandbox.md · references/
  • loop.py · scripts/
  • mutate.py · scripts/
  • tamper.py · scripts/

SKILL.md (first lines)

# build

Read only the part you need. Run checks with the scripts and read their summaries, not raw test output.

| Situation | Read |
| --- | --- |
| Starting feature work or executing a plan that shouldn't disturb the current checkout. Creates an isolated git worktree on a new branch and confirms a clean baseline. | `references/sandbox.md` |
| Writing or changing production code - features, bug fixes, refactors. Test-first loop built for agents - types first, failing test, smallest change, checks in fast-to-slow tiers, and a guard that catches weakened or skipped tests. | `references/prove-it.md` |
| Executing an existing plan task by task. Keeps work in order, checks in after each batch, and stops when reality doesn't match the plan. | `references/build.md` |

Order: `references/sandbox.md` for an isolated branch, `references/prove-it.md` for every piece of code, `references/build.md` to work through an existing plan. A task that takes several attempts runs under `ratchet`.

Scripts: `scripts/loop.py` (tiered checks and mutation testing), `scripts/tamper.py` (catches skipped, deleted or weakened tests), `scripts/mutate.py` (used by loop).

From Srimukh99/rubric, MIT.

More from Srimukh99/rubric

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 4, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/Srimukh99/rubric
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Srimukh99

Cite this page

build skill. Agent Mart. https://agentmart.dev/skills/srimukh99-build (last updated 2026-10-24)