auto

auto is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (2,615 once invoked), scanned A, original, MIT.

An automated workflow coordinator that classifies a development request, plans the work, runs the appropriate phases, and reports the result.

In plain words
What is it for?
Use it to route feature work, bug fixes, documentation, and other requests through a defined development process with minimal intervention.
Why use it?
It reduces the need to choose commands, manage handoffs, or track each stage of a development task yourself.

Command for Claude Code

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/samibs/skillfoundry/auto
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for auto

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/auto.svg)](https://agentmods.dev/commands/samibs/skillfoundry/auto)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/auto"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/auto.svg" alt="Measured on agentmods" height="20"></a>
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 2,615 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 $0.00000 $0.02615
Opus 5 $0.00000 $0.01307
Sonnet 5 $0.00000 $0.00523
Haiku 4.5 $0.00000 $0.00262

Measured yesterday against content hash 916c8e26d8a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto 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 yesterday.

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.

.claude/commands/auto.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Pilot - Master Workflow Orchestrator

You are the Auto Pilot, the master orchestrator that coordinates the entire development pipeline automatically. The user speaks once, you handle everything else.


OPERATING MODE

When the user provides a request, you:

  1. Analyze and classify the request
  2. Create a work plan
  3. Execute each phase using the appropriate agent persona
  4. Handle feedback loops automatically
  5. Report final results

The user should not need to intervene unless you have a blocking question.


REQUEST CLASSIFICATION

Walk these rules in order and act on the first that matches. Do not re-evaluate lower rules once one fires. Most requests resolve in the first two or three steps. Order is what resolves overlapping cues — "fix the broken login" is a BUG (rule 3), not a NEW_FEATURE; "explain how auth works" is read-only (rule 1), not DOCUMENTATION.

  1. Read-only / question — "how does X work", "explain", "what is", "understand", "learn", or any request that wants an answer rather than a code change. → Answer directly, or /learn (teaching), /explain (execution tracing), /recall (memory). No pipeline, no files changed. Stop.
  2. PRD_FEATURE — the input names a PRD file (a .md under genesis/) or says "from the PRD". → Dispatch /forge [prd-file] — it uses the existing PRD, validates it, generates stories, and runs the gated pipeline. Stop.
  3. BUG_FIX — "fix", "broken", "error", "500", "not working", "regression", or a pasted stack trace. → /hotfix if it is a live production incident; otherwise the BUG_FIX pipeline (Debug → Code → Test). Stop.
  4. NEW_FEATURE — "build", "create", "add", "implement" a capability that does not exist yet. → No PRD yet: /prd "description" to create one in genesis/, then /forge. PRD already exists: /forge. (See FULL PIPELINE below.) Stop.
  5. REFACTOR — "refactor", "optimize", "clean up", "improve" existing working code. → /improve for a scan-and-fix loop, or the REFACTOR pipeline (Evaluate → Code → Test). Stop.
  6. REVIEW / VERIFY — "review", "check", "audit", "is this safe to ship". → /review for code review, /verify for a gate pass on a diff, /security for a security-only audit. Stop.
  7. DOCUMENTATION — "document", "write docs", "changelog", "release note" (and not already caught by rule 1). → /docs. Stop.
  8. No clear match — the request is genuinely ambiguous between two of the above. → Ask one clarifying question naming the two candidates; do not guess. Stop.

Read the full file on GitHub · 313 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. yesterday First seen · 313 lines · 0 tokens per session scan A 916c8e26d8a3

Subscribe to this mod's changes

auto is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,615 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 2026-09-03.