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/panishandsome/ai-rules-sync/agents-mdgit clone --depth 1 https://github.com/PanisHandsome/ai-rules-syncWrote 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/instructions/panishandsome/ai-rules-sync/agents-md)<a href="https://agentmods.dev/instructions/panishandsome/ai-rules-sync/agents-md"><img src="https://agentmods.dev/badge/instructions/panishandsome/ai-rules-sync/agents-md.svg" alt="Measured on agentmods" 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 | $0.00367 | $0.00367 |
| Opus 5 | $0.00183 | $0.00183 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
ai-rules-sync AGENTS.md 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 4d 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
agentsync
agentsync converts between AI coding-agent rule files (AGENTS.md, CLAUDE.md, .cursorrules, Copilot, Windsurf) and can scaffold a fresh AGENTS.md. The same engine in src/core/agentsync.js powers both the CLI and the browser playground.
Build & test commands
- Install:
no install needed (Node 18+, zero dependencies) - Dev server:
npm run web # serves the playground at http://localhost:5173 - Test:
npm test
Always run the test and lint commands before finishing a task.
Architecture
src/core/agentsync.jsis the engine and the single source of truth. It imports nothing.bin/agentsync.mjsis the CLI;web/is the browser playground. Both import the engine directly — keep it dependency-free and isomorphic (must run in Node and the browser).- Adding a tool format = add an entry to
FORMATS, a branch inparse(), and a renderer inRENDERERS. Nothing else should need to change. - Things that don't translate between tools (Cursor
globs, Claude@imports) must surface aswarnings, never be silently dropped.
Code style & conventions
- Match the style of surrounding code; do not reformat unrelated lines.
- Prefer small, focused changes and clear names over cleverness.
- Write idiomatic JavaScript (ESM, zero-dependency). Do not add runtime dependencies.
- Add or update a case in
test/run.mjsfor any behavior change.
Before opening a PR
- Tests and lint pass locally.
- No unrelated files changed.
- Public APIs and docs updated if behavior changed.
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.
- 4d ago First seen · 32 lines · 367 tokens per session scan A 56a0df1699fa
ai-rules-sync AGENTS.md is an instructions file published in the GitHub repository PanisHandsome/ai-rules-sync (118 stars, last pushed 3mo ago), licensed MIT. It adds 367 tokens to every session, about $0.0018 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
awesome-grok-build AGENTS.md
Instructions for DominikTobureto/awesome-grok-build, covering agents.md, mission, operating principles, source policy and file conventions.
coding-agent-rules AGENTS.md
Instructions for cskwork/coding-agent-rules, covering ten commandments for coding agents, response & documentation style and repository rules.
vibe-27 AGENTS.md
AGENTS.md instructions for fatalex27/vibe-27, covering vibe-27 behavioral guidelines, 1. editor, not typist, 2. intention over implementation, 3. trust and verify and 4. think before coding.
ruleprobe AGENTS.md
Instructions for moonrunnerkc/ruleprobe, covering agents.md, project, build and test, code style and architecture boundaries.
ruleprobe CLAUDE.md
Instructions for moonrunnerkc/ruleprobe, covering claude.md, project, working style, engineering standards and tooling.
repo2agent copilot-instructions.md
Copilot instructions for Sanmu-27/repo2agent, covering github copilot instructions, repository snapshot, project map, common commands and agent workflow.