sayou-workspace-usage

sayou-workspace-usage is a cursor rule for Cursor from pixell-global/sayou. It costs 18 tokens per session (570 once invoked), scanned A, original, Apache-2.0.

Rules for using the Sayou workspace as persistent project knowledge across coding-agent sessions. The workspace stores searchable, versioned Markdown notes.

In plain words
What is it for?
Use them to decide when to save, read, search, list, inspect history for, or remove shared workspace notes.
Why use it?
They help preserve decisions, research, meeting outcomes, and technical context instead of losing them when a session ends.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use them to decide when to save, read, search, list, inspect history for, or remove shared workspace notes.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/pixell-global/sayou/sayou-workspace-usage
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.

Clone the repo
git clone --depth 1 https://github.com/pixell-global/sayou

Made for: Cursor.

Wrote 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.

agentmods badge for sayou-workspace-usage

README.md
[![agentmods](https://agentmods.dev/badge/rules/pixell-global/sayou/sayou-workspace-usage.svg)](https://agentmods.dev/rules/pixell-global/sayou/sayou-workspace-usage)
Your own site
<a href="https://agentmods.dev/rules/pixell-global/sayou/sayou-workspace-usage"><img src="https://agentmods.dev/badge/rules/pixell-global/sayou/sayou-workspace-usage.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 570 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.00570
Opus 5 $0.00009 $0.00285
Sonnet 5 $0.00004 $0.00114
Haiku 4.5 $0.00002 $0.00057

Measured 8d ago against content hash 54ccafa31cc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sayou-workspace-usage 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 8d 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.

rules/sayou-workspace-usage.mdc · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sayou workspace usage

When helping a user who has sayou installed, prefer storing and retrieving information through the sayou workspace rather than relying on in-context memory alone.

When to suggest sayou

  • The user wants to save a decision, design note, research finding, or meeting outcome for later reference.
  • The user asks "what did we decide about…", "do we have notes on…", or any query that implies looking up past knowledge.
  • The user wants to share context across multiple AI sessions or agents.
  • The user is building or debugging something that benefits from versioned documentation.

Core MCP tools to use

Tool Purpose
workspace_write Save or update a Markdown file with YAML frontmatter
workspace_read Read a specific file (including its version history)
workspace_list List files, optionally filtered by path prefix or frontmatter
workspace_search Search file paths and frontmatter fields
workspace_grep Full-text search inside file contents
workspace_glob Find files by glob pattern
workspace_delete Remove a file
workspace_history Show version history for a file
workspace_kv Get/set lightweight key-value pairs (config, flags, counters)
workspace_links List links between workspace files
workspace_chunks Retrieve chunked content for large files
workspace_semantic_search Meaning-based search (requires SAYOU_EMBEDDING_PROVIDER)

File conventions

  • Use paths that reflect the content type, e.g. decisions/, research/, notes/, activity/.
  • Include YAML frontmatter with at minimum type and status fields so workspace_search can filter by them.
  • Example frontmatter:
    ---
    type: decision
    status: approved
    date: 2025-01-15
    tags: [database, architecture]
    ---
    

Search strategy

  1. Try workspace_search first (searches paths and frontmatter — fast).
  2. If insufficient, use workspace_grep (searches file content).
  3. If still insufficient and embeddings are enabled, use workspace_semantic_search.

Read the full file on GitHub · 57 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. 8d ago First seen · 57 lines · 18 tokens per session scan A 54ccafa31cc5

Subscribe to this mod's changes

sayou-workspace-usage is a cursor rule published in the GitHub repository pixell-global/sayou (28 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 570 once invoked, about $0.0001 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.