10-constitution

A set of project rules covering code quality, safety, technology choices, and how to handle decisions with tradeoffs.

In plain words
What is it for?
Use it to guide implementation choices, protect sensitive information, require verification, and keep changes clear and reviewable.
Why use it?
It sets minimum standards for builds, tests, formatting, secrets, destructive actions, and clear technical decisions.

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/10-constitution
Clone the repo
git clone --depth 1 https://github.com/MarceCandil/agent-context-kit

Made for: Cursor.

Per session 191 This file is loaded in full into every session.
When invoked 191 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 $0.00191 $0.00191
Opus 5 $0.00096 $0.00096
Sonnet 5 $0.00038 $0.00038
Haiku 4.5 $0.00019 $0.00019

Measured yesterday against content hash e6e642503a8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

10-constitution 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/10-constitution.mdc · 29 lines

What it actually says

Constitution (Cursor)

Constitution

Quality gates (must)

  • No broken build: code must typecheck and compile.
  • Add/update tests when behavior changes.
  • Keep formatting/lint clean.

Safety (must)

  • Never exfiltrate secrets (keys/tokens). If found, redact and propose rotation.
  • Do not run destructive commands without explicit confirmation (e.g., delete, reset, drop).

Engineering constraints

  • Prefer TypeScript.
  • Prefer small, reviewable PRs.
  • Avoid “clever” abstractions unless requested; default to clarity.

Decision discipline

  • If a decision has tradeoffs, present 2–3 options with pros/cons and pick one with rationale.
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 · 29 lines · 191 tokens per session scan A e6e642503a8c

Subscribe to this mod's changes

10-constitution is a cursor rule published in the GitHub repository MarceCandil/agent-context-kit (2 stars, last pushed 6mo ago), licensed MIT. It adds 191 tokens to every session, about $0.0010 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.