Borrowing it
Nothing to install: this file belongs to chikingsley/safari-bookmarks-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chikingsley/safari-bookmarks-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/chikingsley/safari-bookmarks-mcpWrote 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/chikingsley/safari-bookmarks-mcp/agents-md)<a href="https://agentmods.dev/instructions/chikingsley/safari-bookmarks-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/chikingsley/safari-bookmarks-mcp/agents-md/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/instructions/chikingsley/safari-bookmarks-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/chikingsley/safari-bookmarks-mcp/agents-md.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 | $0.00443 | $0.00443 |
| Opus 5 | $0.00221 | $0.00221 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
safari-bookmarks-mcp 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 10d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Setup
- Install project dependencies with
uv sync --locked --dev. - Run the full local gate with
just check. - Run supply-chain checks with
just audit. - Install the local pre-push gate with
just install-hookswhen working in a clone.
CI / Local Gates
- Treat
just checkandjust auditas the source of truth for this repo's quality and supply-chain gate. - GitHub-hosted Actions may be unavailable on this account; verify remote Actions with a live probe before relying on them.
- The local pre-push hook runs
just checkandjust audit; bypass only for emergency pushes withSKIP_LOCAL_CI=1.
Dependency Changes
- Treat new runtime dependencies and dependency upgrades as security-sensitive changes.
- Before changing dependencies, inspect the current state with
uv tree --outdated --locked. - Prefer targeted upgrades when fixing a vulnerability; use broad
uv lock --upgradeonly when the resulting diff stays reviewable. - After dependency changes, run
just checkandjust audit. - Do not add new package indexes, direct URLs, Git dependencies, or install scripts unless the user explicitly asks and the risk is documented.
Security Review Focus
- Preserve the MCP server's default write safety: writes require
dry_run=Trueunless the server is started with--confirm-write, and--readonlymust block writes. - Be careful around
~/Library/Safari/Bookmarks.plist; write paths should keep backups, use atomic replacement, and preserve existing file permissions. - Review bookmark tree mutations for cycles, root deletion, malformed paths, and dry-run persistence bugs.
- Keep GitHub Actions least-privilege: explicit permissions, pinned third-party actions, no persisted checkout credentials, and no dependency caches in release or publish jobs.
Review Guidelines
- For dependency bumps, check both behavior and supply-chain risk: lockfile diff, vulnerability audit, release notes for direct dependencies, and CI workflow changes.
- Prioritize bugs that can corrupt bookmarks, silently write to the real Safari plist, leak credentials, or weaken release/publish controls.
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.
- 10d ago First seen · 35 lines · 443 tokens per session scan A fa125f669180
safari-bookmarks-mcp AGENTS.md is an instructions file published in the GitHub repository chikingsley/safari-bookmarks-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 443 tokens to every session, about $0.0022 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.