Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/markmhendrickson/neotomanpx agentmods add skills/markmhendrickson/neotoma/create_ruleWrote 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.
[](https://agentmods.dev/skills/markmhendrickson/neotoma/create_rule)<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/create_rule"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/create_rule/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.
<a href="https://agentmods.dev/skills/markmhendrickson/neotoma/create_rule"><img src="https://agentmods.dev/badge/skills/markmhendrickson/neotoma/create_rule.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00005 | $0.01790 |
| Opus 5.5 | $0.00002 | $0.00716 |
| Sonnet 5.5 | $0.00001 | $0.00358 |
| Haiku 4.5 | $0.00001 | $0.00179 |
Grade A, and why
create_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 1mo 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.
This is a copy
89% identical to create-rule — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Rule
Create a new rule file with _rules suffix and automatically create symlink in .claude/rules/.
SUBMODULE MODE: If a submodule name is provided (e.g., /create-rule foundation), create the rule in that submodule. If no submodule name is provided, create in the main repository's docs/ directory.
Command
create-rule [submodule_name]
Inputs
submodule_name(optional string): Submodule name to create rule in (e.g., "foundation"). If omitted, creates rule in main repository'sdocs/directory.
Workflow Overview
If submodule name provided:
- Verify submodule exists
- Determine submodule rule location
- Prompt user for rule details
- Create rule file in submodule
- Run setup script to create symlink (if applicable)
- Exit after submodule rule creation
If no submodule name provided (default - repo mode):
- Prompt user for rule details
- Create rule file in
docs/{location}/{name}_rules.md - Include standard Agent Instructions template
- Run setup script to create symlink
- Verify symlink created
Tasks
Step 1: Determine Scope
If submodule name provided:
-
Verify submodule exists:
if ! git submodule status <submodule_name> >/dev/null 2>&1; then echo "❌ Submodule not found: <submodule_name>" exit 1 fi -
Determine submodule rule location:
- For
foundationsubmodule:foundation/agent_instructions/cursor_rules/ - For other submodules: Check for standard rule directories or prompt user
- For
-
Set context for submodule rule creation
If no submodule name provided:
- Set context for main repository rule creation in
docs/directory
Step 2: Prompt User for Rule Details
Repository mode prompts:
-
Rule file name (without
_rules.mdsuffix)- Example: "entity_resolution" will become "entity_resolution_rules.md"
- Validate: alphanumeric with underscores only
-
Location in
docs/directory- Options:
conventions,foundation,subsystems,architecture,developer, etc. - Validate: directory must exist or ask to create
- Options:
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.
- 1mo ago First seen · 292 lines · 5 tokens per session scan A 47c5ad42624a
create_rule is a skill published in the GitHub repository markmhendrickson/neotoma (34 stars, last pushed 2d ago), licensed MIT. It adds 5 tokens to every session and 1,790 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to create-rule, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
akf-trust-metadata
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.
bilibili_search
Search for videos on Bilibili using keyword queries generated from user interests.
bernstein-plan
Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution plan before agents start working.
bernstein-run
Run a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and merges results. Also use to check run status, costs, and to verify a finished run against its…
taste-explorer
A guided interview skill that asks focused questions to learn what a person likes and dislikes, then saves confirmed preferences as long-term memory.
bernstein-approve
Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.