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 TheThoughtagen/agentsync --skill ai-configgit clone --depth 1 https://github.com/TheThoughtagen/agentsyncWrote 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/thethoughtagen/agentsync/ai-config)<a href="https://agentmods.dev/skills/thethoughtagen/agentsync/ai-config"><img src="https://agentmods.dev/badge/skills/thethoughtagen/agentsync/ai-config/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/thethoughtagen/agentsync/ai-config"><img src="https://agentmods.dev/badge/skills/thethoughtagen/agentsync/ai-config.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 | $0.00036 | $0.00671 |
| Opus 5.5 | $0.00014 | $0.00268 |
| Sonnet 5.5 | $0.00007 | $0.00134 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
ai-config 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 2mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Configuration with AgentSync
Canonical Source of Truth
The .ai/ directory is the single source of truth for all AI tool configurations. Never edit synced copies directly — always edit files in .ai/ and then sync.
File Purposes
| File | Purpose |
|---|---|
.ai/instructions.md |
Main project instructions. Synced to CLAUDE.md, AGENTS.md, and .cursor/rules/project.mdc. |
.ai/hooks.toml |
Event hook definitions (pre/post tool use, shell execution, etc.). |
.ai/mcp.toml |
MCP (Model Context Protocol) server definitions. |
.ai/plugins.toml |
Plugin references and configuration. |
aisync.toml |
AgentSync configuration — controls sync strategy per tool (symlink, copy, generate). Lives at project root. |
Subdirectories
| Directory | Purpose |
|---|---|
.ai/memory/ |
Context files providing persistent knowledge across sessions. |
.ai/rules/ |
Coding rules with YAML frontmatter (style, conventions, patterns). |
.ai/commands/ |
Slash command definitions for AI tools. |
.ai/skills/ |
Skill modules that teach AI tools domain-specific knowledge. |
.ai/agents/ |
Agent definitions for multi-agent workflows. |
Conditional Tags
Use conditional tags to include content only for specific tools:
<!-- aisync:claude-only -->
This content only appears in Claude Code output.
<!-- /aisync:claude-only -->
<!-- aisync:cursor-only -->
This content only appears in Cursor output.
<!-- /aisync:cursor-only -->
<!-- aisync:opencode-only -->
This content only appears in OpenCode output.
<!-- /aisync:opencode-only -->
Content outside conditional tags is included in all tool outputs.
Critical Rules
-
Always edit canonical
.ai/files. Never edit synced copies directly. The following are generated outputs and will be overwritten on sync:CLAUDE.md.cursor/rules/project.mdcAGENTS.md
-
Run
aisync sync(or/aisync:sync) after making changes to propagate updates to all configured tools.
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.
- 2mo ago First seen · 71 lines · 36 tokens per session scan A e611cbf1c55c
ai-config is a skill published in the GitHub repository TheThoughtagen/agentsync (2 stars, last pushed 7mo ago), licensed MIT. It adds 36 tokens to every session and 671 once invoked, about $0.0001 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.
ai-config compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-configTheThoughtagen/agentsync | Skill | 2 | 7mo ago | MIT | A | 36 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |