What is workspace-knowledge?

A set of workspace rules for answering architecture, integration, contract, and cross-repository questions using indexed project knowledge.

Investigating how repositories connect, checking known gaps, finding symbols or contracts, and reviewing the impact of code changes.

It defines how to retrieve evidence, handle incomplete indexes, resolve conflicting information, and cite workspace paths.

workspace-knowledge — Cursor rule for Cursor by fabiodepin

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/fabiodepin/contractmesh

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/fabiodepin/contractmesh/workspace-knowledge/github.svg)](https://agentmods.dev/rules/fabiodepin/contractmesh/workspace-knowledge)

Your own site

<a href="https://agentmods.dev/rules/fabiodepin/contractmesh/workspace-knowledge"><img src="https://agentmods.dev/badge/rules/fabiodepin/contractmesh/workspace-knowledge/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/fabiodepin/contractmesh/workspace-knowledge"><img src="https://agentmods.dev/badge/rules/fabiodepin/contractmesh/workspace-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 838 This file is loaded in full into every session.

When invoked 838 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00838	$0.00838
Opus 5.5	$0.00335	$0.00335
Sonnet 5.5	$0.00168	$0.00168
Haiku 4.5	$0.00084	$0.00084

Measured 2mo ago against content hash 5881f3bfd3d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

workspace-knowledge 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 2mo 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.

.cursor/rules/workspace-knowledge.mdc · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workspace knowledge (MCP)

For cross-repo, integration, architecture, contract or known-gap questions:

Required flow

Call index_status first. If recommend_rebuild is true or missing_chunks_count > 0, ask the user to run contractmesh index.
Use fetch_hits as the primary retrieval call.
If fetch_hits returns truncated: true, use get_chunk(chunk_id) or get_doc_chunks(doc_id) for the missing text.
Use search_docs only for broader exploration or symbol-only lookup.
Read files directly only when the index is insufficient.
Mention workspace-relative path values in answers. Do not persist chunk_id values in human docs.
Prefer sources with higher trust_level when they conflict (confirmed > accepted > known_risk > detected_mismatch > implementation > inferred > suggestion).
Cite trust_level in Sources consulted when MCP returns it.

Examples

Cross-repo: fetch_hits("example greeting behavior", kind=["contract"], repo=["app","web"])
Gap: fetch_hits(gap="APP-KG-001")
Symbol: fetch_hits("ExampleService", kind=["code_anchor"], include_main_chunk=false)
PR review: pr_impact(base="main", head="HEAD")
Before editing code: preflight_change(symbol="ExampleService.greet")
Before editing by path: preflight_change(paths=["src/pages/UserPage.tsx"])
Before editing a contract: preflight_change(contract_ids=["FE-UI-SHELL-001"])
Before marking done: completion_check(paths_changed=["src/pages/UserPage.tsx"])

Preflight (before patching)

Call preflight_change with at least one of symbol/symbols, paths, or contract_ids before editing. Prefer the natural target (path for a view, contract_id for a contract edit, symbol for a service method).
Read card.text first (Risk, Why, Review, Run). Use details only when you need full evidence.
If agent_policy.requires_confirmation is true (typically risk: HIGH), stop and ask the user to confirm they reviewed the listed contracts/gaps/tests. Do not patch until confirmed.
Risk thresholds come from contractmesh.yml → preflight:.
Explicit contract_ids are strong caller intent — treat returned contracts as the requested grounding, not as inferred relevance.

Read the full file on GitHub · 76 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.

2mo ago First seen · 76 lines · 838 tokens per session scan A 5881f3bfd3d7

Subscribe to this mod's changes

workspace-knowledge is a cursor rule published in the GitHub repository fabiodepin/contractmesh (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 838 tokens to every session, about $0.0034 per session on Opus 5.5. 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 2026-08-31.

Memory and context

mempalace-recall-always

Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.

MemPalace/mempalace · 260 tokens

dreamd-recall

Search dreamd at the start of a task and quote a hit. Append when the user corrects you or states a decision.

botzrDev/dreamd · 136 tokens

session-memory

Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.

major7apps/pensyve · 22 tokens

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…

shalomeir/common-memory-bank · 1,801 tokens

self-improving-obsidian-llm-wiki

LLM Wiki OS operating rules.

Bahgs/Self-Improving-Obsidian-LLM-Wiki · 146 tokens

memsprout

Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.

memsprout/agents · 519 tokens