brief

brief is a command for Claude Code from Maksim-Burtsev/punchcard. It costs 24 tokens per session (304 once invoked), scanned A, original, MIT.

A command that creates a short orientation brief for a GitHub pull request, GitLab merge request, branch, or change range. A brief explains the shape and scope of a change before review; it is not itself a review.

In plain words
What is it for?
Use it to brief a pull request, merge request, current branch, or branch comparison before code review.
Why use it?
It gives a reviewer grounded context about what changed and how the parts fit together before they look for problems.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the punchcard plugin — 1 skill, 2 commands shipped together

Good fit Use it to brief a pull request, merge request, current branch, or branch comparison before code review.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/maksim-burtsev/punchcard/brief
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/Maksim-Burtsev/punchcard

Made for: Claude Code.

Or install punchcard, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

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 brief

README.md
[![agentmods](https://agentmods.dev/badge/commands/maksim-burtsev/punchcard/brief/github.svg)](https://agentmods.dev/commands/maksim-burtsev/punchcard/brief)
Your own site
<a href="https://agentmods.dev/commands/maksim-burtsev/punchcard/brief"><img src="https://agentmods.dev/badge/commands/maksim-burtsev/punchcard/brief/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 brief

Your own site · 80×15
<a href="https://agentmods.dev/commands/maksim-burtsev/punchcard/brief"><img src="https://agentmods.dev/badge/commands/maksim-burtsev/punchcard/brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 304 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 $0.00024 $0.00304
Opus 5 $0.00012 $0.00152
Sonnet 5 $0.00005 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured 5d ago against content hash 627a8953ad86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

brief 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 5d 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/brief.md · 27 lines

What it actually says

Run the punchcard brief on the given target.

Target: $ARGUMENTS — a GitHub PR / GitLab MR URL, or a branch or range in the current repository. No argument: the current branch against the repository's default branch. Standing on the default branch with no argument there is nothing to brief, and the brief says exactly that in one line and stops.

Write the brief of that change exactly as skills/punchcard/BRIEF.md prescribes — it lives next to the punchcard skill — including its four sections, its grounded map, its rule that nothing is cut to fit, and its ban on findings. The brief renders in the conversation and is never posted into the PR/MR. BRIEF.md is the single source of truth; this command only names the target.

Two things about the reply itself. The user's own words around this command set the language of the brief: a user who wrote their message in Russian gets the brief in Russian, whatever language this command, the skill file, the diff and the description are in; only the four section titles stay in English. And the reply is the brief alone, starting at its bold header line — no sentence before it about being ready to write it.

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. 5d ago First seen · 27 lines · 24 tokens per session scan A 627a8953ad86

Subscribe to this mod's changes

brief is a command published in the GitHub repository Maksim-Burtsev/punchcard (1 stars, last pushed 6d ago), licensed MIT. It adds 24 tokens to every session and 304 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 2026-09-04.