newrule

A command for adding a lint rule, a check that detects unwanted patterns in code or documents. It requires examples that should trigger and should not trigger the rule, implementation details, two tests, and a full check run.

In plain words
What is it for?
Use it when creating a new rule in the project’s linter and validating both its behavior and its boundaries.
Why use it?
It exposes false positives—careful work incorrectly flagged by a linter—before a rule is accepted. It also records the rule’s source, suggested fix or question, and severity.

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/alinotfoundbtw/sounding/newrule
Clone the repo
git clone --depth 1 https://github.com/alinotfoundbtw/sounding

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 269 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 $0.00016 $0.00269
Opus 5 $0.00008 $0.00134
Sonnet 5 $0.00003 $0.00054
Haiku 4.5 $0.00002 $0.00027

Measured 2d ago against content hash 705edcb584eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

newrule 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 2d 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/newrule.md · 24 lines

What it actually says

Add a rule to $ARGUMENTS.

Follow the sequence, and do not skip step 2:

  1. Write the failing fixture first — the artifact that should trigger it.
  2. Write the fixture that must NOT trigger it. A plausible, well-written artifact that a careless pattern would catch. If you cannot think of one, the rule is probably too broad to add.
  3. Implement the rule in src/sounding/rules/. It needs:
    • a reference — the spec section or documented practice. Not optional.
    • a fix string, or a question with options when intent is required
    • a severity: 15 / 7 / 3. When unsure, pick lower.
  4. Two tests: fires on the bad case, silent on the good case.
  5. Run /check.
  6. Report the rule code, both fixtures, and what severity you chose and why.

Reminder: false positives are how a linter loses its audience. A rule that fires on careful work is worse than no rule.

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. 2d ago First seen · 24 lines · 0 tokens per session scan A 705edcb584eb

Subscribe to this mod's changes

newrule is a command published in the GitHub repository alinotfoundbtw/sounding (4 stars, last pushed 7d ago), licensed MIT. It adds 16 tokens to every session and 269 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 2026-08-31.