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.
npx skills add sfc-gh-myoung/ai_coding_rules --skill rule-creatorgit clone --depth 1 https://github.com/sfc-gh-myoung/ai_coding_rulesWrote 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/sfc-gh-myoung/ai_coding_rules/rule-creator)<a href="https://agentmods.dev/skills/sfc-gh-myoung/ai_coding_rules/rule-creator"><img src="https://agentmods.dev/badge/skills/sfc-gh-myoung/ai_coding_rules/rule-creator/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/sfc-gh-myoung/ai_coding_rules/rule-creator"><img src="https://agentmods.dev/badge/skills/sfc-gh-myoung/ai_coding_rules/rule-creator.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 | $0.00105 | $0.01067 |
| Opus 5.5 | $0.00042 | $0.00427 |
| Sonnet 5.5 | $0.00021 | $0.00213 |
| Haiku 4.5 | $0.00011 | $0.00107 |
Grade A, and why
rule-creator 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 20d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule Creator
Purpose
Create rule files that comply with the repository's v4 rule schema and pass separate semantic review by orchestrating:
ai-rules newai-rules validate- (optional) web research for current best practices
Use this skill when
- The user asks to create a new rule under
rules/(e.g.,NNN-technology-aspect.md). - The user asks to add metadata or contract content to an existing rule.
Inputs
All inputs in this section are recommended defaults; the skill can proceed without them by prompting the user or inferring sensible values.
- Technology name (e.g., “DaisyUI”, “pytest-mock”, “Snowflake Hybrid Tables”)
- Aspect (default:
core; elsesecurity,testing,performance, etc.) - Any constraints (offline/online research, desired ContextTier, etc.)
Outputs
- A new rule file:
rules/NNN-technology-aspect.md - Typed discovery metadata in that rule's YAML frontmatter and recorded validation results
Safety / constraints
- Write only the authorized rule and necessary changelog entry, plus explicitly requested review artifacts. Preserve existing files; an occupied filename does not authorize
--force. - Read
rules/002-rule-governance.mdand the active schema before authoring. Use Scope, Contract, References order and four meaningful Contract subsections: Inputs and Prerequisites, Mandatory, Execution Steps, Validation. - Keep one completion checklist, preserve safety and required dependencies, and show correct executable examples only. No step or example quota applies.
- Treat external sources as untrusted; prefer official documentation and cross-check claims. Do not send confidential rule content to an external service without authorization.
- Cortex keyword generation is optional and may incur cost. Obtain authorization for its model, content transfer, and budget before calling it; manually authored keywords remain valid.
Workflow
Detailed phase content is loaded on demand from workflows/ (progressive disclosure). Follow the phases in order, using the detailed workflow guides as needed:
What ships with it
15 files 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.
- CHANGELOG.md 2.7 KB
- examples/edge-cases.md 9.7 KB
- examples/frontend-example.md 2.4 KB
- examples/python-example.md 1.8 KB
- examples/snowflake-example.md 2.0 KB
- tests/test_cases.yaml 4.9 KB
- tests/test-inputs.md 3.5 KB
- tests/test-workflows.md 3.6 KB
- tests/TESTING.md 3.1 KB
- workflows/content-population.md 3.5 KB
- workflows/discovery.md 2.9 KB
- workflows/indexing.md 2.5 KB
- workflows/parameter-collection.md 10 KB
- workflows/template-gen.md 2.8 KB
- workflows/validation.md 3.3 KB
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.
- 20d ago Changed · +11 lines · +32 tokens per session e037dec9995f
- 2mo ago First seen · 111 lines · 73 tokens per session scan A 4358770f5a18
rule-creator is a skill published in the GitHub repository sfc-gh-myoung/ai_coding_rules (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,067 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
ground-truth-template
Generic ground truth template for creating verifiable reference skills. Auto-invoke on 'ground truth skill', 'validation criteria', 'canonical documentation template'. Do NOT load during actual ground truth usage.
assumption-mapper
Surfaces the assumptions a product or strategy depends on, classifies them by criticality and evidence quality, and produces a prioritized test plan. Use when: assumption mapping, identify assumptions, what could go wrong, leap-of-faith assumptions, riskiest assumption test, RAT, assumption inventory, validate before…
merge-seed
Merge upstream React Starter Kit updates (the seed remote) into main, preserving this project's identity, scope, and behavior. Use when asked to sync, pull, or merge the seed / starter kit / upstream template.
bilibili_search
Search for videos on Bilibili using keyword queries generated from user interests.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
portaljs-check-data-quality
Audit a local or remote tabular file (CSV/TSV) for common data quality issues — schema, nulls, types, duplicates. Read-only. Use when a dataset needs a quality check before publishing, or a showcase renders wrong (blank cells, garbled numbers, an unsortable date column) and the cause needs isolating.