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.
git clone --depth 1 https://github.com/pixell-global/sayouWrote 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/rules/pixell-global/sayou/sayou-workspace-usage)<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>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 | $0.00018 | $0.00570 |
| Opus 5 | $0.00009 | $0.00285 |
| Sonnet 5 | $0.00004 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
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.
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
typeandstatusfields soworkspace_searchcan filter by them. - Example frontmatter:
--- type: decision status: approved date: 2025-01-15 tags: [database, architecture] ---
Search strategy
- Try
workspace_searchfirst (searches paths and frontmatter — fast). - If insufficient, use
workspace_grep(searches file content). - If still insufficient and embeddings are enabled, use
workspace_semantic_search.
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.
- 8d ago First seen · 57 lines · 18 tokens per session scan A 54ccafa31cc5
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.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
context-recorder-system
A modular system for recording project context, decisions, requirements, and lessons in structured files. It divides the recorder into core, template, advanced, and edge-case modules.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.