00-agents

A project guide that explains how an AI coding assistant should work in a particular code repository, including its commands, rules, roles, and workflows.

In plain words
What is it for?
Use it to set up project instructions, run development and verification commands, and follow feature, bug-fix, review, or deployment workflows.
Why use it?
It gives the assistant the repository’s expectations and checks, reducing guesswork and keeping changes small and consistent.

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/marcecandil/agent-context-kit/00-agents
Clone the repo
git clone --depth 1 https://github.com/MarceCandil/agent-context-kit

Made for: Cursor.

Per session 406 This file is loaded in full into every session.
When invoked 406 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 $0.00406 $0.00406
Opus 5 $0.00203 $0.00203
Sonnet 5 $0.00081 $0.00081
Haiku 4.5 $0.00041 $0.00041

Measured yesterday against content hash 4682cb3ee6cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

00-agents 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/00-agents.mdc · 44 lines

What it actually says

AGENTS (Cursor)

AGENTS.md

How to work in this repo (required)

  • Read .cursor/rules/30-map.mdc and .cursor/rules/10-constitution.mdc first.
  • If any requirement is unclear, ask for clarification or inspect the codebase. Do not guess.
  • Prefer small, reviewable diffs. Keep changes scoped.

Commands (edit to match your project)

  • Install: pnpm install
  • Dev: pnpm dev
  • Typecheck: pnpm typecheck
  • Tests: pnpm test
  • Lint: pnpm lint
  • Sync AI files: pnpm sync:ai

Verification (run after changes)

After making changes, verify your work:

  1. pnpm typecheck — must pass
  2. pnpm lint — must pass
  3. pnpm test — must pass
  4. pnpm sync:ai && git diff --exit-code — generated files must stay in sync

Workflows (Windsurf/Cascade or manual)

  • Feature: ai/workflows/feature-dev.md
  • Bugfix: ai/workflows/bug-fix.md
  • PR Review: ai/workflows/pr-review.md
  • Deploy: ai/workflows/deploy.md

Roles

  • Tech Lead: .cursor/rules/20-roles.mdc (tech-lead section)
  • Dev: .cursor/rules/20-roles.mdc (dev section)
  • QA: .cursor/rules/20-roles.mdc (qa section)
  • DevOps: .cursor/rules/20-roles.mdc (devops section)
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 · 44 lines · 406 tokens per session scan A 4682cb3ee6cd

Subscribe to this mod's changes

00-agents is a cursor rule published in the GitHub repository MarceCandil/agent-context-kit (2 stars, last pushed 6mo ago), licensed MIT. It adds 406 tokens to every session, about $0.0020 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.