A command that prepares an autonomous build run for an approved software feature. It checks the feature plan and project-origin rules, creates an automation file from a template, and shows the command that starts the external driver.

Use it with an approved feature plan to validate prerequisites, create specs/ /automation.json, and get the driver command.

It catches missing approval or validation problems before an automated build is launched.

auto-build — Command by gosha70

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add commands/gosha70/code-copilot-team/auto-build

Clone the repo

git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 622 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00622
Opus 5	$0.00000	$0.00311
Sonnet 5	$0.00000	$0.00124
Haiku 4.5	$0.00000	$0.00062

Measured 2d ago against content hash 8132e30e8d7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-build scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

adapters/claude-code/.claude/commands/auto-build.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scaffold and explain an autonomous build run for an approved SDD feature. Validates the approval + origin gates, writes specs/<feature-id>/automation.json from the template, and prints the driver command — the driver itself runs OUTSIDE this session.

Usage: /auto-build <feature-id> [profile] (profile defaults to advisory)

Prerequisites

specs/<feature-id>/plan.md exists with status: approved (Plan Approval Gate)
jq must be installed
A gating reviewer configured in ~/.code-copilot-team/providers.toml

Steps

1. Validate the feature

If specs/<feature-id>/plan.md is missing or its frontmatter is not status: approved, stop: the Plan Approval Gate is a human gate — the autonomy design never bypasses it.
Run bash scripts/validate-spec.sh --feature-id <feature-id>; stop on failure.
Run bash scripts/check-origin-alignment.sh <feature-id>; if exit >= 2, surface the three-resolution escalation (rescope / restart / document divergence) and stop.

2. Scaffold automation.json

If specs/<feature-id>/automation.json does not exist, copy shared/templates/sdd/automation-template.json there and fill in with the user:

branch.name / branch.base (never a default branch as the working branch)
test.command — the command the driver runs to verify each phase (required)
review.reviewers[0].provider — must match a provider in providers.toml with a healthcheck; keep gating: true
profile — only advisory is available in this increment
Caps: keep the defaults unless the user asks (phases 8, fix sessions 3, wall-clock 4h, cost $25)

Show the resulting JSON to the user before writing it.

3. Verify the reviewer

Run bash scripts/providers-health.sh --provider <gating-reviewer>. If it fails, help the user fix providers.toml before proceeding.

4. Print the run command — do NOT execute it

The driver must run outside any copilot session (fresh session per phase is the whole point). Print:

scripts/auto-build-loop.sh <feature-id> [--dry-run]

Read the full file on GitHub · 58 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 58 lines · 0 tokens per session scan A 8132e30e8d7c

Subscribe to this mod's changes

auto-build is a command published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 622 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Planning Productivity

auto-build

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Prerequisites

Steps

1. Validate the feature

2. Scaffold automation.json

3. Verify the reviewer

4. Print the run command — do NOT execute it

What this file has done since we first saw it

Other commands, from other repositories

git

checklist

clarify

specify

analyze

constitution