autobuild

An automated system for carrying out software improvement cycles through stages such as research, planning, implementation, and testing, with multiple agents reviewing the work. An agent is an automated worker that performs a defined task.

In plain words
What is it for?
Use it to implement features, fix bugs, refactor code, clean up unused code, or improve quality through structured iterations.
Why use it?
It addresses shallow fixes, scope drift, lost reasoning, and changes that have not been independently checked.

Skill for Claude CodeCodex

Part of the autobuild plugin — 4 skills, 1 command, 1 agent shipped together

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 skills/stellarshenson/claude-code-plugins/autobuild
Any agent
npx skills add stellarshenson/claude-code-plugins --skill autobuild
Clone the repo
git clone --depth 1 https://github.com/stellarshenson/claude-code-plugins

Made for: Claude Code, Codex.

Or install autobuild, the plugin that ships this one along with the rest of its 4 skills, 1 command, 1 agent.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,262 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.

ModelPer sessionOnce invoked
Fable 5 $0.00080 $0.02262
Opus 5 $0.00040 $0.01131
Sonnet 5 $0.00016 $0.00452
Haiku 4.5 $0.00008 $0.00226

Measured 2d ago against content hash e58900489383, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autobuild 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.

plugins/autobuild/skills/autobuild/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autobuild - Autonomous Iteration Orchestrator

Breaks improvement work into phases. Spawns agent panels per stage. Enforces quality via two independent gates. Use for iteration, quality improvement, bug fixes, refactors, GC, feature implementation.

Solves:

  • Shallow fixes - forces research and hypothesis before implementation
  • Scope creep - plan locks scope, review catches deviations
  • Benchmark overfit - guardian agent blocks benchmark-specific tuning
  • Lost context - hypothesis catalogue persists across iterations
  • Unchecked quality - two independent gates catch incomplete work
  • No accountability - every phase logs agents, outputs, verdicts in YAML

Phase instructions, agent definitions, exit criteria live in resources/. Run start to see what each phase requires.

Pre-flight install (MANDATORY - run every session, no asking)

Always run this single line BEFORE invoking orchestrate. No-op when the package is already importable; auto-installs when missing OR when a stale shim is on PATH but the package is uninstalled in the active Python:

python3 -m pip install --user --upgrade stellars-claude-code-plugins 2>&1 | tail -1
LIB=$(python3 -c "import importlib.metadata as m;print(m.version('stellars-claude-code-plugins'))" 2>/dev/null) || { echo "FATAL: toolkit unavailable"; exit 1; }
PLUG=$(grep -m1 '"version"' "${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json" 2>/dev/null | cut -d'"' -f4)
OLDER=$(printf '%s\n%s\n' "$LIB" "$PLUG" | sort -V | head -1)
[ -n "$PLUG" ] && [ "$LIB" != "$PLUG" ] && [ "$OLDER" = "$LIB" ] && { echo "STALE: library $LIB older than plugin $PLUG - refusing to run on an outdated CLI; re-run the upgrade"; exit 1; }
echo "toolkit $LIB"

Run the CLI without touching the caller's project. The gate above puts it on PATH, so the bare command name is the whole invocation. uv run instead resolves whatever project the working directory sits in and writes uv.lock and .venv into it, so if you reach for uv pass --no-project (uv run --no-project <cli> ...) - it skips project discovery, leaves the tree untouched and still finds the same PATH binary. --no-sync and --frozen are not substitutes; both still create .venv.

Read the full file on GitHub · 195 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.

  1. 2d ago First seen · 195 lines · 80 tokens per session scan A e58900489383

Subscribe to this mod's changes

autobuild is a skill published in the GitHub repository stellarshenson/claude-code-plugins (3 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 2,262 once invoked, about $0.0004 per session on Opus 5. 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens