project

A project rule set that tells coding agents which instructions, methods, files, and safety checks to follow in a repository.

In plain words
What is it for?
It is for following repository guidance, using the documented test-driven development process, recording bugs and decisions, and running the required checks before pushing.
Why use it?
It gives agents one source of truth for project conventions and prevents inconsistent changes, such as editing protected files or duplicating skill instructions.

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/craigcossairt/trellis/project
Clone the repo
git clone --depth 1 https://github.com/craigcossairt/trellis

Made for: Cursor.

Per session 317 This file is loaded in full into every session.
When invoked 317 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 $0.00317 $0.00317
Opus 5 $0.00159 $0.00159
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00032 $0.00032

Measured 2d ago against content hash 6c063e294911, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project 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.

.cursor/rules/project.mdc · 24 lines

What it actually says

Read AGENTS.md at the repo root and follow it - it is the canonical instruction file for all AI agents on this project. Full methodology docs live in docs/methodology/ (TDD workflow, bug-fix protocol, session habits). Append bug patterns to docs/common-gotchas.md and decisions to docs/decision-log.md as described in AGENTS.md § Autonomous Housekeeping.

Guardrail hooks for Cursor are wired in .cursor/hooks.json (same scripts Claude Code runs; trust the workspace so they load). Honor the rules they enforce even if hooks aren't firing: never edit secrets or lock files, and run bash bin/verify-green.sh before pushing when the push gate is configured.

Skills in .cursor/skills/ are routers, not procedures. Each is frontmatter plus one sentence naming a canonical file under .claude/ - read that file when a router matches the task, and never fork its body into the router. Copy the canonical description verbatim: in Cursor it is the trigger, so a reworded one silently stops matching phrases the canonical skill answers to.

While this directory exists, adding a skill or command under .claude/ means adding its router in the same commit; hooks CI fails either half of that pair going missing. If the project drops Cursor support, delete .cursor/ outright and the rule no longer applies.

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 · 24 lines · 317 tokens per session scan A 6c063e294911

Subscribe to this mod's changes

project is a cursor rule published in the GitHub repository craigcossairt/trellis (4 stars, last pushed 12d ago), licensed MIT. It adds 317 tokens to every session, about $0.0016 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.