hotfix

hotfix is a command for Claude Code from dinhnguyenngoc/spec-driven-claude-code. It costs 29 tokens per session (3,208 once invoked), scanned A, original, MIT.

A command for restoring a live system after a serious problem by choosing a rollback or a forward fix, then patching, checking, and redeploying it. A rollback returns to an earlier release; a forward fix repairs the current line.

In plain words
What is it for?
Use it for live-service incidents when you need an audit trail, a rollback-or-fix decision, mandatory verification, and redeployment.
Why use it?
Production incidents need a fast, traceable recovery process. This command requires the repaired version to pass real-environment verification before promotion.

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/dinhnguyenngoc/spec-driven-claude-code/hotfix
Clone the repo
git clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-code

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 hotfix

README.md
[![agentmods](https://agentmods.dev/badge/commands/dinhnguyenngoc/spec-driven-claude-code/hotfix.svg)](https://agentmods.dev/commands/dinhnguyenngoc/spec-driven-claude-code/hotfix)
Your own site
<a href="https://agentmods.dev/commands/dinhnguyenngoc/spec-driven-claude-code/hotfix"><img src="https://agentmods.dev/badge/commands/dinhnguyenngoc/spec-driven-claude-code/hotfix.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,208 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 $0.00029 $0.03208
Opus 5 $0.00015 $0.01604
Sonnet 5 $0.00006 $0.00642
Haiku 4.5 $0.00003 $0.00321

Measured 4d ago against content hash 083ac7c50d14, 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 4d 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/hotfix.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/hotfix — Production Hotfix

"Restore service first, then make it permanent."

Purpose

Workspace Mode: if the session root declares Mode: workspace → resolve the target repo per CLAUDE.md §Workspace Mode before anything else; every path, probe, and gate below is relative to the target repo, and the workspace disk-check applies at the gate.

Restore a released artifact currently running live to a correct state, under time pressure, with a full audit trail. /hotfix is a thin orchestrator: it does NOT re-implement the bug-fixing logic (reuses /fix-issue), does NOT re-implement artifact testing (reuses /verify), does NOT re-implement promotion (reuses /deploy). Its unique value lies in the 3 things those other commands deliberately do not do:

/verify policy override: In the standard pipeline, Gate 11 (/verify) is step optional · BLOCKING if run. Inside /hotfix, Gate 11 is promoted to REQUIRED — no exceptions. The patch must PASS /verify on the new digest before /deploy promotes it. When calling /deploy from Step 5, set env HOTFIX_MODE=1 so /deploy enforces that reports/VERIFY_REPORT.md exists.

  1. Rollback-vs-fix-forward triage — decide the fastest & safest recovery before touching code.
  2. Patch release ceremony — bump patch version, CHANGELOG, release notes for the patch.
  3. Post-incident — re-verify the patch on the real artifact + update the runbook so it doesn't happen again.

When to Use

Use /hotfix only when all three conditions are true: (a) the artifact is deployed / live, (b) it is affecting real users / has a severity level, (c) the patch must be shipped again with version + audit.

Situation Correct command
/build or /test fails during coding /debug
Bug report but not yet released / normal sprint flow /fix-issue
Bug on a live artifact, needs urgent patch + re-ship /hotfix
Project has never been deployed (still in dev) /fix-issue (nothing "hot" to fix)

Read the full file on GitHub · 169 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. 4d ago First seen · 169 lines · 29 tokens per session scan A 083ac7c50d14

Subscribe to this mod's changes

hotfix is a command published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 6d ago), licensed MIT. It adds 29 tokens to every session and 3,208 once invoked, about $0.0001 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 2026-08-30.