hotfix

A branch-based command for handling a top-priority production fix, known as a P0 hotfix. It diagnoses the problem, implements a fix, opens a ready-for-review pull request, and performs verification and review afterward.

In plain words
What is it for?
Use it when a critical issue needs a quick branch, code fix, pull request, and follow-up verification and review.
Why use it?
It provides a defined fast path for urgent problems while postponing some checks until after the pull request is opened.

Command

Part of the swe-workbench plugin — 1 skill, 24 commands, 32 agents, 4 hooks 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 commands/lugassawan/swe-workbench/hotfix
Clone the repo
git clone --depth 1 https://github.com/lugassawan/swe-workbench

Or install swe-workbench, the plugin that ships this one along with the rest of its 1 skill, 24 commands, 32 agents, 4 hooks.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 700 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 $0.00032 $0.00700
Opus 5 $0.00016 $0.00350
Sonnet 5 $0.00006 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured 2d ago against content hash a3a418e80460, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hotfix 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.

commands/hotfix.md · 28 lines

What it actually says

Hotfix request: $ARGUMENTS

If $ARGUMENTS contains a ticket reference, invoke swe-workbench:ticket-context first and prepend its structured summary to the delegation context below. Skip if $ARGUMENTS is free-text with no recognizable ref. (Trigger patterns are defined in that skill's "When to invoke" section.)

Interrogation mode. Before producing anything, resolve the mode:

  • Explicit signal in the invocation is honored without asking. grill-me = --grill, "grill me", or "grill-me mode". standard = --standard, "standard", or "quick". Strip the signal from $ARGUMENTS and record the resolved mode.
  • No explicit signal: ask via AskUserQuestion — one question, header "Mode", options Standard (recommended, listed first) and Grill me. Standard description: "Lightweight clarify — a restatement and at most one question, then proceed." Grill-me description: "Relentlessly walk the decision tree one question at a time, each with a recommended answer, self-answering from the codebase where possible." Use the user's choice.

Standard mode: proceed with the command's existing lightweight clarify (a restatement and at most one clarifying question) — do not ask the mode question again.

Grill-me mode: activate swe-workbench:workflow-grill and run its interrogation loop to completion (exit on shared understanding or when the user says "proceed"). Then thread the emitted ## Resolved decisions block into the command's normal artifact/delegation step below — the same way a ticket-context summary is prepended — and continue as in standard mode.

Activate the swe-workbench:workflow-hotfix skill. It owns the reordered lifecycle — a plain branch (never a worktree), a minimal fix with TDD relaxed, a ready-for-review PR opened before verification and review, then verify + review running against the open PR, then a reconcile step that strips the deferred-verification marker only if the regression test was backfilled and verification is green.

Absolute rules:

  • Always branch, never worktree — git checkout -b hotfix/<slug> off the synced default branch. This command exists specifically to skip worktree ceremony.
  • Always open the PR ready-for-review, never draft — speed is the point.
  • Verification and review always run after the PR is opened, never before — this command's entire identity is deferred verification. Do not reorder to verify-then-PR; that is /swe-workbench:implement.
  • Write the deferred-verification marker (<!-- swe-workbench:deferred-verification -->) into the PR body at open time. Strip it only if the regression test is backfilled AND verification is green, before requesting merge — never strip it preemptively.
  • If the ticket lacks acceptance criteria, stop and ask the user — do not invent scope, even under time pressure.
  • Do not invent architectural answers — escalate any genuine design fork to swe-workbench:senior-engineer.
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 · 28 lines · 32 tokens per session scan A a3a418e80460

Subscribe to this mod's changes

hotfix is a command published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 700 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 2026-08-31.