/add-claude-rule

A slash command for adding a written rule to CLAUDE.md, a project file that gives guidance to the Claude coding assistant. It places the rule under the most relevant section or creates one.

In plain words
What is it for?
Use it when you want to record a project-specific instruction in CLAUDE.md and see the resulting unified diff.
Why use it?
It avoids manually finding the right section and formatting the change, while keeping the edit limited to one new bullet point.

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/liam-hq/liam/add-claude-rule
Clone the repo
git clone --depth 1 https://github.com/liam-hq/liam

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 300 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 $0.00021 $0.00300
Opus 5 $0.00010 $0.00150
Sonnet 5 $0.00004 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured yesterday against content hash 14f66dcdb537, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

/add-claude-rule 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/add-claude-rule.md · 27 lines

What it actually says

You are a repository assistant responsible for keeping CLAUDE.md up to date.

  1. Translate the text provided via $ARGUMENTS into clear, concise English.
  2. Locate the best section:
    • Scan all headings at level‑2 or deeper (##, ###, etc.) in CLAUDE.md (i.e., exclude only the level‑1 title).
    • Choose the heading whose text most closely matches the rule’s topic (simple case‑insensitive keyword overlap is enough).
    • If no suitable heading is found, create a new level‑2 heading whose title is a concise description of the rule’s theme (e.g., the first key noun phrase) and place it at the end of the file.
  3. Append the translated rule as a bullet point (- ) directly beneath the chosen or newly created heading.
  4. Save the file.

Output format

# Unified Git diff for CLAUDE.md

Notes

  • Make no other edits to the file.
  • Always add the rule as a single bullet point.
  • Show only the added/removed lines in the diff; avoid unrelated whitespace changes.
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 · 27 lines · 21 tokens per session scan A 14f66dcdb537

Subscribe to this mod's changes

/add-claude-rule is a command published in the GitHub repository liam-hq/liam (5,100 stars, last pushed 3d ago), licensed Apache-2.0. It adds 21 tokens to every session and 300 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 2026-08-30.