goma

goma is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (379 once invoked), scanned A, original, MIT.

An autonomous mode for the project implementation command that runs a PRD-driven pipeline without waiting for the developer at each decision.

In plain words
What is it for?
Use it to implement PRDs hands-off, resume or roll back runs, and optionally execute stories in parallel.
Why use it?
It lets trusted requirements run unattended while recording decisions that were deferred and requiring conditions needed for reliable rollback.

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/goma
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 goma

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/goma.svg)](https://agentmods.dev/commands/samibs/skillfoundry/goma)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/goma"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/goma.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 379 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 $0.00379
Opus 5 $0.00000 $0.00189
Sonnet 5 $0.00000 $0.00076
Haiku 4.5 $0.00000 $0.00038

Measured yesterday against content hash eae16ac5c693, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goma 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/goma.md · 36 lines

What it actually says

/goma - Go Mode Autonomous

/goma is a thin alias for /go --mode=autonomous. It runs the full /go pipeline hands-off: escalations are auto-resolved where safe and otherwise deferred and logged for post-run review. Use only when you trust the PRDs.

Persona: See agents/fixer-orchestrator.md for auto-remediation. Reflection Protocol: See agents/_reflection-protocol.md.


Dispatch

/goma [args]/go --mode=autonomous [args] with full argument passthrough.

/goma genesis/auth.md      →  /go --mode=autonomous genesis/auth.md
/goma --parallel           →  /go --mode=autonomous --parallel
/goma --resume             →  /go --mode=autonomous --resume
/goma --rollback           →  roll back the last autonomous run

What autonomous mode adds

A clean git working tree is REQUIRED (unlike semi-auto). Autonomous rollback depends on it, and rollback must be reliable when the developer is not watching.

Pre-flight — blocks execution if any item is unmet:

  • All PRDs pass critical validation
  • No interrupted state exists (or --resume was chosen)
  • Git working tree is clean — autonomous rollback depends on it
  • State machine initialized with a rollback manifest
  • Escalation log cleared or archived from the previous run

If the tree is dirty, autonomous mode is blocked with instructions to commit or stash first. During the run, every escalation is deferred and written to the escalation log for review rather than interrupting execution. Everything else — pipeline phases, Anvil gates, batching, delivery audit — is /go's behavior unchanged.

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 · 36 lines · 0 tokens per session scan A eae16ac5c693

Subscribe to this mod's changes

goma is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 379 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.