project-context

A project-memory rule that reads and maintains a MASTER_CONTEXT.md file, a repository document containing decisions such as brand voice, default products, and API lessons.

In plain words
What is it for?
Use it at the start of substantial repository work and after major changes to preserve context, setup requirements, and dated project learnings.
Why use it?
It keeps important project knowledge available across coding sessions and avoids repeatedly asking for the same details. It also records significant workflow or product changes for later reference.

Cursor rule for Cursor

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 rules/novoads/agent-skills/project-context
Clone the repo
git clone --depth 1 https://github.com/novoads/agent-skills

Made for: Cursor.

Per session 466 This file is loaded in full into every session.
When invoked 466 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 $0.00466 $0.00466
Opus 5 $0.00233 $0.00233
Sonnet 5 $0.00093 $0.00093
Haiku 4.5 $0.00047 $0.00047

Measured yesterday against content hash 73f6dbab1c4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-context 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 yesterday.

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/project-context.mdc · 16 lines

What it actually says

Project context

  • If .env or MASTER_CONTEXT.md do not exist, tell the user to run ./scripts/setup.sh.
  • At the start of substantive work in this repo, read MASTER_CONTEXT.md at the repository root for brand voice, default product, and API learnings. It carries no prices — that is deliberate.
  • The first time the user asks to generate something and MASTER_CONTEXT.md is missing a field that request needs (default product, brand voice), ask for it then — once — and write the answer back so no future session asks again. A setup-only session asks for nothing and reports almost nothing: close with the setup-close template in AGENTS.md ("First-time setup" — a status line, "What you can ask for now", the product-photos line) and keep git mechanics and sync details out unless they block an ask. Never write a credit number into it.
  • After significant changes (new workflows, verified Novoads behaviors, brand updates), append a short dated entry to the Changelog section in MASTER_CONTEXT.md.
  • For Novoads HTTP usage, prompts, and polling, follow .cursor/skills/novoads-api/SKILL.md and linked reference.md.
  • Session work-product goes in a gitignored homegenerated/ (renders), outputs/<job>/ (video downloads + edit workfiles), prompts/ (composed prompts), iterations/ (clone rounds), logs/. Never invent a new top-level directory; leave git status as clean as you found it. Stated in full in AGENTS.md ("Every session").
  • Never quote a credit cost from memory. Prices come from a live POST /v1/estimates in the current session, shown and approved before anything is generated. For a video where the model speaks, the spoken line is approved separately, first.
  • Log every generation call to logs/novoads-api.jsonl — observability only, never a pricing source.
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. yesterday First seen · 16 lines · 466 tokens per session scan A 73f6dbab1c4e

Subscribe to this mod's changes

project-context is a cursor rule published in the GitHub repository novoads/agent-skills (9 stars, last pushed 6d ago), licensed MIT. It adds 466 tokens to every session, about $0.0023 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 2026-08-31.