claude-sdk-rs: Command for Claude Code

.claude/commands/patch.md

patch is a command for Claude Code from bredmond1019/claude-sdk-rs. It costs 0 tokens per session (825 once invoked), scanned A, original, Apache-2.0.

A lightweight workflow for low-risk hotfixes and documentation-only changes. It implements the change, validates it, and commits it, while deliberately skipping testing, review, and documentation stages.

In plain words
What is it for?
Use it for a self-evident change affecting one file or a tightly connected pair, when no new tests are needed. Larger or behaviour-changing work should use a fuller workflow.
Why use it?
It keeps very small changes from going through a full development process. Its scope warning helps avoid using it for behaviour, API, schema, or interface changes that need more checks.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is bredmond1019/claude-sdk-rs's own configuration. It tells Claude Code how to work on claude-sdk-rs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-sdk-rs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/patch.md
Clone the repo
git clone --depth 1 https://github.com/bredmond1019/claude-sdk-rs

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 patch

README.md
[![agentmods](https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/patch/github.svg)](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/patch)
Your own site
<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/patch"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/patch/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 patch

Your own site · 80×15
<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/patch"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/patch.svg" alt="Reviewed on agentmods" width="80" 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 825 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 $0.00000 $0.00825
Opus 5.5 $0.00000 $0.00330
Sonnet 5.5 $0.00000 $0.00165
Haiku 4.5 $0.00000 $0.00082

Measured 11d ago against content hash f18cc6e14f2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

patch 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 11d 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/patch.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/patch — Lightweight hotfix pipeline

Warning: This workflow skips test, review, and document stages. Use only for low-risk hotfixes. If you are unsure whether a change is patch-scope, use /sdlc-flow instead.

What this is

A stripped-down pipeline for hotfixes and docs-only changes: implement → validate → commit. No test report, no review stage, no document stage. Appropriate when:

  • The change touches one file (or a tightly coupled pair).
  • No new tests are needed (no new logic introduced).
  • No API surface, schema, or interface changes.
  • The fix is self-evidently correct and low blast-radius.

/patch is the bottom rung of the pipeline ladder. When a change is bigger than a hotfix, Step 1 redirects you up the ladder rather than stretching /patch past its remit:

Rung When Engine
/patch trivial, self-evident hotfix or docs-only; no new test this command
lean /sdlc-task small, but it changes behaviour and needs a test (implement → fast-test → fix loop → commit) /sdlc-task <slug>
/sdlc-flow a whole spec (full lifecycle, review + PR) /sdlc-flow <slug>

Instructions

Step 1 — Scope check (the ladder)

Before doing anything, confirm the change is patch-scope. Answer each question, and redirect up the ladder at the first "yes":

  1. Does the change touch more than two files? → If yes, stop and redirect (see below).
  2. Does the change introduce new logic / behaviour that should be proven by a test? → If yes, stop and redirect to lean /sdlc-task (its fast-test→fix loop is exactly for small, tested changes).
  3. Does the change affect an API endpoint, schema, or public interface, or span a whole spec? → If yes, stop and redirect to /sdlc-flow (full lifecycle, review + PR).

If you cannot answer all three with "no", output the matching redirect and stop:

SCOPE CHECK FAILED — this change is not patch-scope.
Redirect:
  - small but needs a test  →  /sdlc-task <spec-slug>      (lean: implement → fast-test → fix → commit)
  - a whole spec            →  /sdlc-flow <spec-slug>       (full lifecycle + review + PR)

Read the full file on GitHub · 76 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. 11d ago First seen · 76 lines · 0 tokens per session scan A f18cc6e14f2a

Subscribe to this mod's changes

patch is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 825 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 2026-10-26.

Related

patch compared with commands from other repositories

patch next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
patchbredmond1019/claude-sdk-rsCommand231mo agoApache-2.0A0Claude Code
standupvvedantb/evaCommand101yesterdayMITA0Claude Code
gitazrtydxb/procoderCommand21111d agoApache-2.0A20Claude Code
session-reportdamusix/atomic-claudeCommand1154d agoMITA31Claude Code
commitechoVic/blade-codeCommand18124d agoMITA8Claude Code
git-workflowHermeticOrmus/LibreUIUX-Claude-CodeCommand1151mo agoMITA14Claude Code
commitjoaquimscosta/arkhe-claude-pluginsCommand2221d agoMITA11Claude Code