agentmods.dev

SiftMarks AGENTS.md

Repository-specific instructions for SiftMarks, a local-first TypeScript monorepo that turns browser bookmarks into searchable AI-assisted memory. A monorepo stores several related packages and apps in one repository.

In plain words
What is it for?
Use it when importing, searching, indexing, tagging, or finding duplicate bookmarks; working on the command-line tool, dashboard, browser extension, database, or MCP server; or running builds and type checks.
Why use it?
It explains the package and app boundaries, available commands, and how to run tests without touching the user's real bookmark database.

Instructions file for CodexOpenCode

24 +1 2mo ago A scan 473 tokens original MIT
View the source file Lling0000/SiftMarks
Install

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.

agentmods
npx agentmods add instructions/lling0000/siftmarks/agents-md
Clone the repo
git clone --depth 1 https://github.com/Lling0000/SiftMarks

Made for: Codex, OpenCode.

Per session 473 This file is loaded in full into every session.
When invoked 473 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00473 $0.00473
Opus 5 $0.00236 $0.00236
Sonnet 5 $0.00095 $0.00095
Haiku 4.5 $0.00047 $0.00047

Measured 2d ago against content hash fbb97ea97dba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SiftMarks 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 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.

AGENTS.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SiftMarks Agent Notes

Project Shape

SiftMarks is a local-first TypeScript monorepo for turning browser bookmarks into searchable AI memory.

  • packages/shared: shared types and utility functions.
  • packages/db: SQLite schema and data access through better-sqlite3.
  • packages/core: bookmark import, parsing, search, duplicate detection, rescue suggestions, and browser bookmark detection.
  • packages/ai: mock, OpenAI-compatible, and Ollama-compatible AI providers.
  • packages/indexer: FTS indexing, summaries, tags, and embeddings.
  • apps/cli: siftmarks command-line interface.
  • apps/mcp-server: MCP stdio server for AI clients.
  • apps/web: Next.js local dashboard and API routes.
  • apps/chrome-extension: Chrome extension that talks to the local web API on port 4399.

Commands

  • Install: npm install
  • Build non-web packages, CLI, and MCP server: npm run build:packages
  • Build everything: npm run build
  • Run the web dashboard: npm run dev
  • Run the CLI after building: node apps/cli/dist/index.js
  • Typecheck: npm run typecheck

Use SIFTMARKS_HOME=/tmp/siftmarks-test for smoke tests that should not touch the user's real ~/.siftmarks database.

Current Caveats

  • The web app has its own rules in apps/web/AGENTS.md; read that file before editing anything under apps/web.
  • The root typecheck command can surface web/Next configuration issues. Do not assume package-level builds prove the web app is production-buildable.
  • The Chrome extension assumes the web app is running at http://localhost:4399.
  • AI calls must stay disabled unless a provider is explicitly configured; mock mode is the default.

Working Rules

  • Do not perform git actions unless the user explicitly asks.
  • Keep changes scoped to the requested area.
  • Prefer existing package boundaries over adding new cross-package shortcuts.
  • Treat local bookmark databases and browser profile files as user data; use temporary data directories for tests when possible.
  • When changing data writes, preserve the local-first behavior and avoid silent external network calls.

Read the full file on GitHub · 42 lines

Changes

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.

  1. 2d ago First seen · 42 lines · 473 tokens per session scan A fbb97ea97dba

Subscribe to this mod's changes

SiftMarks AGENTS.md is an instructions file published in the GitHub repository Lling0000/SiftMarks (24 stars, last pushed 2mo ago), licensed MIT. It adds 473 tokens to every session, about $0.0024 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.

Analytics and metricsDatabasesMemory and contextagentsai-memoryai-toolsbookmark-managerbookmarksbrowser-extension
Related

Other instructions, from other repositories

hindsight CLAUDE.md

Instructions for vectorize-io/hindsight, covering claude.md, project overview, development commands, local development (api + ui) and start both api server and control plane ui.

vectorize-io/hindsight · 4,846 tokens

mulch AGENTS.md

Instructions for jayminwest/mulch, covering agents.md, what this project is, tech stack at a glance, project layout and commands.

jayminwest/mulch · 2,678 tokens

agentor copilot-instructions.md

Instructions for CelestoAI/agentor: Read AGENTS.md in the repository root. It is the single source of contributor guidance for this project — architecture, development setup, code style, testing, and CI — and applies to Copilot exactly as written.

CelestoAI/agentor · 141 tokens

teak AGENTS.md

Instructions for praveenjuge/teak, covering teak agent guide, start here, architecture invariants, convex work and verification.

praveenjuge/teak · 854 tokens

mem9 AGENTS.md

Instructions for unvulcanised-watercress762/mem9, covering what this repo is, high-level modules, commands, go server build / verify and single go test.

unvulcanised-watercress762/mem9 · 1,827 tokens

agent-knowledge-cards AGENTS.md

Instructions for manojbajaj95/agent-knowledge-cards, covering agents.md, layout, on-disk cards, commands and rules.

manojbajaj95/agent-knowledge-cards · 861 tokens