hotfix

hotfix is a command for Claude Code from samibs/skillfoundry. It costs 23 tokens per session (886 once invoked), scanned A, original, MIT.

An emergency production-fix command for addressing incidents with a shortened implementation and testing process.

In plain words
What is it for?
Use it for urgent crashes, failing endpoints, or resource problems; it performs a security scan, applies a minimal fix, runs smoke tests, commits the change, and records an audit trail.
Why use it?
It helps restore a broken production system quickly while recording the bypasses and creating follow-up work for the remaining debt.

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/hotfix
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 hotfix

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/hotfix.svg)](https://agentmods.dev/commands/samibs/skillfoundry/hotfix)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/hotfix"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/hotfix.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 886 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 $0.00023 $0.00886
Opus 5 $0.00012 $0.00443
Sonnet 5 $0.00005 $0.00177
Haiku 4.5 $0.00002 $0.00089

Measured yesterday against content hash 81255579a2db, 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 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/hotfix.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/hotfix — Emergency Fix Pipeline

USE ONLY FOR PRODUCTION INCIDENTS This skill bypasses gates. Every bypass is logged. Every hotfix creates follow-up debt. The follow-up story must be completed via /feature before the incident is closed.


Activation

/hotfix "null pointer crash on checkout when cart is empty"
/hotfix "login endpoint returning 500 on all OAuth callbacks"
/hotfix "memory leak causing OOM kills in the worker pool"

What This Does

/hotfix [description]

  Step 0: Declare incident + load execution context
  Step 1: Semgrep HARD BLOCK scan (secrets/SQL injection — always active)
  Step 2: Implement the minimal fix
  Step 3: Smoke test — max 2 iterations (changed files only)
  Step 4: Commit with hotfix: prefix + bypass disclosure
  Step 5: Create genesis/hotfix-followup-*.md (mandatory)
  Step 6: Write audit entry to logs/audit-trail.jsonl

Pipeline Diagram

/hotfix "description"
     │
     ▼
[Step 0] DECLARE INCIDENT ──────── Print bypass list
     │
     ▼
[Step 1] SEMGREP HARD BLOCK ──── ERROR severity only
     │                           (never bypassed, even in hotfix)
  CLEAN                      BLOCKED
     │                           │
     ▼                           └── HALT: fix security issue first
[Step 2] IMPLEMENT FIX ─────────── Minimal, no cleanup, read files first
     │
     ▼
[Step 3] SMOKE TEST ─────────────── Max 2 iterations, changed files only
     │
 PASSING                       FAILING after 2
     │                             │
     ▼                             └── Ask: --accept-failing or abort?
[Step 4] COMMIT ─────────────────── hotfix: prefix, bypass disclosure
     │
     ▼
[Step 5] FOLLOW-UP STORY ───────── genesis/hotfix-followup-*.md (MANDATORY)
     │
     ▼
[Step 6] AUDIT TRAIL ────────────── logs/audit-trail.jsonl + logs/hotfixes.md
     │
     ▼
  HOTFIX COMPLETE

Bypassed Gates

Gate Status
Shadow tester review ⏭ BYPASSED
Anvil quality gates ⏭ BYPASSED
Evaluator ⏭ BYPASSED
Full TestLoop (5 iter) ⏭ BYPASSED — smoke test only
Documentation codifier ⏭ BYPASSED — follow-up covers this
Semgrep HARD BLOCK ✅ ALWAYS ACTIVE
Audit trail ✅ ALWAYS ACTIVE

Read the full file on GitHub · 125 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 · 125 lines · 23 tokens per session scan A 81255579a2db

Subscribe to this mod's changes

hotfix is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 886 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 2026-09-03.