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 agentmods add skills/lbb00/ai-rules-sync/update-knowledge-basenpx skills add lbb00/ai-rules-sync --skill update-knowledge-basegit clone --depth 1 https://github.com/lbb00/ai-rules-syncWhat 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 | $0.00021 | $0.00398 |
| Opus 5 | $0.00010 | $0.00199 |
| Sonnet 5 | $0.00004 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
update-knowledge-base 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.
What it actually says
Update Knowledge Base
Purpose
Automatically analyze recent code changes and update the project's knowledge base documentation to reflect current architecture, features, and conventions.
Instructions
-
Analyze Recent Changes
- Review git diff or recent commits
- Identify new adapters, commands, or features
- Note architectural changes or new patterns
-
Read Current Knowledge Base
- Check if KNOWLEDGE_BASE.md exists
- If not, create it with proper structure
- If exists, identify sections needing updates
-
Update Sections
- Architecture: Update if new adapters or core components added
- Features: Document new CLI commands or options
- Conventions: Note any new coding patterns established
- API Changes: Document breaking changes or deprecations
-
Verify Accuracy
- Cross-reference with actual source code
- Ensure examples are runnable
- Check that all documented features exist
-
Format Consistently
- Use consistent markdown formatting
- Include code examples where helpful
- Maintain table format for command references
Knowledge Base Structure
# AI Rules Sync - Knowledge Base
## Architecture Overview
- Adapter system description
- CLI layer structure
- Config management
## Supported Tools
| Tool | Types | Source Dir | Target Dir |
## Commands Reference
| Command | Description | Example |
## Adapter Implementation
- How to add new adapters
- Required interfaces
## Configuration
- ai-rules-sync.json structure
- Local/private rules
## Changelog
- Recent significant changes
Output
After running this skill:
- KNOWLEDGE_BASE.md is created or updated
- Changes reflect current codebase state
- Documentation is accurate and complete
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.
- 2d ago First seen · 74 lines · 21 tokens per session scan A 2eda062a1ca0
update-knowledge-base is a skill published in the GitHub repository lbb00/ai-rules-sync (37 stars, last pushed 13d ago), licensed Unlicense. It adds 21 tokens to every session and 398 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.
Other skills, from other repositories
authoring-skills-and-rules
Author Skills (SKILL.md) and rules/instructions across Claude Code, Cursor, OpenCode, Codex, and GitHub Copilot. Covers frontmatter, file layout, activation model, cross-platform mirroring, and the universal craft: progressive disclosure, trigger-rich descriptions (context pointers), leading words, token budget…
karpathy-guidelines
Tool-agnostic behavioral guidelines for AI coding assistants. Use when writing, reviewing, debugging, or refactoring code to reduce overengineering, surface ambiguity, make surgical changes, and define verifiable success criteria.
spec-driven
Structured planning pipeline with 4 adaptive phases (Specify, Design, Tasks, Execute) and persistent knowledge accumulation for development teams. Auto-sizes depth by complexity from quick fixes to multi-component features. Commands: /explore (understand problem + map context), /plan (write spec → design → tasks)…
skill-memory
Use skill-memory to download, view and edit agent skills in memory. TRIGGER by 'skill', 'memory', 'learn'.
valyu-best-practices
Complete Valyu API toolkit for AI agents. Use this skill when asked to perform real-time search across web, academic, medical, transportation, financial sources, content extraction from URLs, AI-powered answers with citations, or comprehensive deep research reports.
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…