update-rules

update-rules is a skill for Claude Code from neuromechanist/research-skills. It costs 114 tokens per session (1,346 once invoked), scanned A, original, BSD-3-Clause.

A skill for comparing project rule files such as AGENTS.md, CLAUDE.md, and .rules/ with newer templates and preparing updates.

In plain words
What is it for?
Use it to check, preview, merge, or apply project-level rule updates; user-level instruction installation is handled separately.
Why use it?
It helps keep agent instructions current without silently overwriting project-specific changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

Part of the project plugin — 15 skills, 5 commands, 3 agents shipped together

Good fit Use it to check, preview, merge, or apply project-level rule updates; user-level instruction installation is handled separately.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/neuromechanist/research-skills/update-rules
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.

Any agent
npx skills add neuromechanist/research-skills --skill update-rules
Clone the repo
git clone --depth 1 https://github.com/neuromechanist/research-skills

Made for: Claude Code.

Or install project, the plugin that ships this one along with the rest of its 15 skills, 5 commands, 3 agents.

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 update-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/neuromechanist/research-skills/update-rules/github.svg)](https://agentmods.dev/skills/neuromechanist/research-skills/update-rules)
Your own site
<a href="https://agentmods.dev/skills/neuromechanist/research-skills/update-rules"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/update-rules/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 update-rules

Your own site · 80×15
<a href="https://agentmods.dev/skills/neuromechanist/research-skills/update-rules"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/update-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,346 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 73
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00114 $0.01346
Opus 5 $0.00057 $0.00673
Sonnet 5 $0.00023 $0.00269
Haiku 4.5 $0.00011 $0.00135

Measured 11d ago against content hash ddd7991b92a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

update-rules 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.

plugins/project/skills/update-rules/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Rules and Configuration

Update existing AGENTS.md/CLAUDE.md and .rules/ files from the latest plugin templates. Non-destructive: never overwrite user customizations, always preview changes before applying.

When to Use

  • After plugin templates have been updated with new rules or improvements
  • When adding a rule file introduced after initial project setup
  • When checking if project rules are current with latest best practices
  • When checking existing project rules against newer templates. For installing or updating user-level instructions across Claude, Codex, Copilot, or Cursor, use install-user-instructions instead.
  • When a user wants to know what changed in the templates since they last synced

Two Operating Levels

Project Level (/update-rules project)

Update the current project's configuration:

  1. .rules/ directory sync -- Compare each template rule file against the project's .rules/ directory:

    • MISSING -- new in templates, not in project. Show purpose and offer to add.
    • CHANGED -- exists but differs from template. Show unified diff, suggest merge.
    • CURRENT -- matches template. Report as up to date.
    • CUSTOM -- user-added rule not in templates. Preserve completely, report.
  2. AGENTS.md section comparison -- Extract H2 headers from both template and project AGENTS.md. Identify missing sections. For matching sections, compare content and suggest updates. Preserve all project-specific customizations (replaced placeholders, custom guidelines, architecture maps). If the project only has CLAUDE.md, offer to migrate shared content into AGENTS.md and leave CLAUDE.md as the Claude adapter.

  3. What gets compared:

    • Template rules/*.md vs .rules/*.md
    • Template AGENTS.md sections vs ./AGENTS.md sections (script emits PROJECT_SECTION_SOURCE=agents|claude so a CLAUDE.md fallback is never silently treated as AGENTS.md)
    • The CLAUDE.md adapter check is performed as an LLM read step (verify it begins with @AGENTS.md and contains only Claude-specific additions), not part of the script output

Read the full file on GitHub · 107 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 107 lines · 114 tokens per session scan A ddd7991b92a6

Subscribe to this mod's changes

update-rules is a skill published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 114 tokens to every session and 1,346 once invoked, about $0.0006 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.