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 instructions/nicepkg/vsync/claude-mdgit clone --depth 1 https://github.com/nicepkg/vsyncWhat 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 | $0.01829 | $0.01829 |
| Opus 5 | $0.00915 | $0.00915 |
| Sonnet 5 | $0.00366 | $0.00366 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
vsync CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories โ prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing โ 276 lines โ stays where its author put it; the contents beside it link to each section on GitHub.
vsync - AI Coding Tool Config Synchronizer
Single source of truth โ Compile to multiple formats โ Diff-based sync
Syncs Skills, MCP, Agents & Commands across Claude Code, Cursor, OpenCode, Codex.
๐ฏ Core Concept
NOT: File copy tool IS: Config compiler + diff executor
Source (Claude Code) โ Normalize โ Diff โ Plan โ Compile โ Atomic Write โ Update Manifest
๐จ Critical Rules (Read FIRST)
1. Follow Documentation Order
Before ANY work:
1. Read TASKS.md โ Find current phase & task
2. Read docs/prd.md Section 2 โ Config formats (MOST IMPORTANT!)
3. Follow TDD โ Write tests FIRST
2. Config Format Precision (See PRD Section 2.2)
// โ ๏ธ CRITICAL: Each tool has DIFFERENT formats
// OpenCode
{ "mcp": { "type": "stdio", "environment": { "X": "{env:VAR}" } } }
// ^^^ ^^^^^^ ^^^^^^^^^^^
// NOT mcpServers! Required! Curly braces!
// Claude Code
{ "mcpServers": { "env": { "X": "${VAR}" } } }
// No type field ^^^^^^^
// Dollar sign, no env: prefix
// Cursor
{ "mcpServers": { "env": { "X": "${env:VAR}" } } }
// No type field ^^^^^^^^^^^^
// Dollar sign WITH env: prefix
3. Environment Variables
// โ WRONG - Expands variables
const config = { env: { TOKEN: process.env.GITHUB_TOKEN } };
// โ
CORRECT - Preserves syntax
const config = { env: { TOKEN: "${env:GITHUB_TOKEN}" } };
4. File Operations
// โ WRONG - Not crash-safe
await fs.writeFile(path, content);
// โ
CORRECT - Atomic write
import { atomicWrite } from "./utils/atomic-write";
await atomicWrite(path, content);
5. Development Workflow
1. TASKS.md โ Pick task
2. Write TEST first (TDD)
3. Implement code
4. pnpm test && pnpm typecheck && pnpm lint
5. Mark [x] in TASKS.md
6. Commit (Angular convention)
๐ Documentation Map
| Document | When to Read | Contains |
|---|---|---|
| TASKS.md | Before every task | Current phase, task breakdown, progress |
| docs/prd.md | When implementing | Complete spec, config formats |
| docs/config.md | When needed | Project configuration values |
| .claude/commands/do-task.md | Shortcut | TDD workflow, patterns, validation |
| .claude/commands/create-task.md | Shortcut | Task creation templates |
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 ยท 276 lines ยท 1,829 tokens per session scan A d46023287e9d
vsync CLAUDE.md is an instructions file published in the GitHub repository nicepkg/vsync (57 stars, last pushed 7mo ago), licensed MIT. It adds 1,829 tokens to every session, about $0.0091 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 instructions, from other repositories
Cyber-AI-Forge AGENTS.md
Instructions for tanghaojie/Cyber-AI-Forge, covering ai ๅไฝ่งๅ, ไบบ็ฑปไฟฎๆนไผๅ ไธๅฒ็ชๅค็, git ๅฎๅ จ้จ็ฆไธ ai ๆไบคๆ ่ฎฐ, ๅผๅงไฟฎๆนๅ็ๆๅญๅบ็กฌ้จ็ฆ and ai ่ชๅจๆไบค็ๅผบๅถๆ ่ฎฐ.
claudekit AGENTS.md
Instructions for duthaho/claudekit, covering agents.md, what this is, build, test, run, architecture and conventions & gotchas.
herdr-cache-alert CLAUDE.md
Instructions for AltanS/herdr-cache-alert, covering claude.md โ working agreement for this repo, the claim contract โ mandatory, versioning โ mandatory, build / run and architecture โ the four layers.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md โ using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) โ same for every tool and workflows.
coograph brutal-honesty.instructions.md
Global communication style โ applies to all workspaces and conversations.
coograph styling.instructions.md
Conventions for CSS/styling files โ loaded only when editing styles.