yolo-abort

yolo-abort is a command for Claude Code from frankxai/Starlight-Intelligence-System. It costs 31 tokens per session (431 once invoked), scanned A, original, MIT.

An emergency stop command for a running multi-step agent session, saving partial state and recording what happened.

In plain words
What is it for?
Use it to interrupt a session, undo reversible in-progress Git changes, and finalize an audit record.
Why use it?
It lets you halt work safely when an action must stop immediately, while tracking any incomplete rollback or pushed changes.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Part of the starlight-intelligence-system plugin — 6 skills, 121 commands, 7 agents shipped together

Good fit Use it to interrupt a session, undo reversible in-progress Git changes, and finalize an audit record.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/frankxai/starlight-intelligence-system/yolo-abort
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.

Clone the repo
git clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-System

Made for: Claude Code.

Or install starlight-intelligence-system, the plugin that ships this one along with the rest of its 6 skills, 121 commands, 7 agents.

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 yolo-abort

README.md
[![agentmods](https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/yolo-abort/github.svg)](https://agentmods.dev/commands/frankxai/starlight-intelligence-system/yolo-abort)
Your own site
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/yolo-abort"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/yolo-abort/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for yolo-abort

Your own site · 80×15
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/yolo-abort"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/yolo-abort.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 431 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00031 $0.00431
Opus 5 $0.00015 $0.00216
Sonnet 5 $0.00006 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured 7d ago against content hash b8de487543a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

yolo-abort 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 7d 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.

.claude/commands/yolo-abort.md · 39 lines

What it actually says

/yolo-abort — Immediate Halt

Kill switch. Use when /yolo is mid-action and you need to stop NOW. Cleaner than Ctrl-C because it saves partial state and runs the safe-rollback path.

Halt sequence

  1. Halt in-flight action — if a Bash command is running, signal interrupt; if an Edit/Write is pending, drop the change.

  2. Roll back in-flight git where reversible:

    • git restore --staged . if files were staged but not committed
    • git reset HEAD~1 --soft if a commit just landed but no push happened
    • Do NOT force-push to undo an already-pushed commit (per spec §7.1 NEVER rules) — record as drift instead
  3. Audit log finalize with abort flag:

    {"event": "session-abort", "ts": "<ISO>", "reason": "<from user or 'unspecified'>",
     "in_flight_action": "<from last audit line>",
     "rollback_status": "<success | partial | drift-recorded>"}
    
  4. Drift event recording: if rollback was partial (e.g., commit was already pushed), write entry to memory/_audit/yolo/_drift.jsonl so next session-open surfaces it.

  5. Operational vault note: append abort entry with timestamp + reason + rollback status. Strategic vault is NOT touched on abort — strategic-class decisions require a clean ship.

  6. Phase-in counter NOT incremented on abort — aborted sessions don't count toward the 3-session phase-in unlock review.

Output

Final message: abort reason + rollback summary + drift flag count + path to audit log file + any operator follow-up actions.


Built on SIP · /yolo-abort · v1.0.0

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. 7d ago First seen · 39 lines · 31 tokens per session scan A b8de487543a9

Subscribe to this mod's changes

yolo-abort is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 431 once invoked, about $0.0002 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 2026-09-03.