claude-code-autoconfig: Command for Claude Code

.claude/commands/gimme-one-liner.md

gimme-one-liner is a command for Claude Code from design-and-deliver/claude-code-autoconfig. It costs 0 tokens per session (685 once invoked), scanned A, original, MIT.

A command that compresses the latest investigation, debugging thread, or diagnosis into exactly three lines: cause, conclusion, and fix.

In plain words
What is it for?
Use it to summarize what caused a problem, where it stands, and what remains to be done.
Why use it?
It removes the lengthy investigation trail once the result is known, making the final status quick to read.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is design-and-deliver/claude-code-autoconfig's own configuration. It tells Claude Code how to work on claude-code-autoconfig 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-code-autoconfig configures →

Reuse

Borrowing it

Nothing to install: this file belongs to design-and-deliver/claude-code-autoconfig. 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/design-and-deliver/claude-code-autoconfig/main/.claude/commands/gimme-one-liner.md
Clone the repo
git clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfig

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 gimme-one-liner

README.md
[![agentmods](https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/gimme-one-liner/github.svg)](https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/gimme-one-liner)
Your own site
<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/gimme-one-liner"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/gimme-one-liner/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 gimme-one-liner

Your own site · 80×15
<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/gimme-one-liner"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/gimme-one-liner.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 685 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 $0.00685
Opus 5 $0.00000 $0.00342
Sonnet 5 $0.00000 $0.00137
Haiku 4.5 $0.00000 $0.00068

Measured 10d ago against content hash 1a4762eb32f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gimme-one-liner 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 10d 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/gimme-one-liner.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gimme One-Liner

Collapse whatever was just investigated in this conversation into exactly three lines.

This command exists because a finished investigation is usually reported at the length it took to conduct — the false starts, the tools that disagreed, the evidence trail. That narration is worth having while the work is live and worthless once it lands. This is the landing form.

Scope

The subject is the most recent investigation, debugging thread, or diagnosis in this conversation — not the whole session, and not the last thing you happened to say. If the conversation moved on to unrelated work after the investigation closed, the investigation is still the subject.

You already know the answer. Do not re-run tools, re-read files, or re-verify to write this — it is a compression of context you hold, not a fresh pass. The one exception: if you are about to state something as fact that you never actually confirmed, check it or drop it.

Output — exactly three lines

**Root cause:** <the mechanism, in one sentence>
**Conclusion:** <where it stands now, in one sentence>
**Fix:** <what remains to be done, in one sentence — or "None." >

Nothing before the first line, nothing after the last. No preamble, no heading, no recap, no closing offer, no bullets, no table.

Rules per line:

  • Root cause names the mechanism, not the symptom. "The log wrote (complete) before the result was known" is a mechanism; "beeps were silent" is a symptom. If the root cause was never actually established, say so plainly — Root cause: not established; <what is known> — rather than promoting the leading theory to a finding.
  • Conclusion is the current state: fixed, fixed-and-tested, open, or won't-fix. Name the commit hash if there is one. This is where an outcome that contradicts an earlier claim in the conversation gets stated, briefly and without re-litigating it.
  • Fix is what is still outstanding. If the work is done, this is None. — do not restate the fix that already landed, which belongs to Conclusion. Anything discovered along the way but deliberately not done goes here in a clause, not a paragraph.

Read the full file on GitHub · 58 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. 10d ago First seen · 58 lines · 0 tokens per session scan A 1a4762eb32f6

Subscribe to this mod's changes

gimme-one-liner is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 685 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 2026-08-31.