00-overview

A shared rulebook for the project's core coding agents, such as architecture, implementation, testing, security, and review agents. It defines their responsibilities and the standards they must follow.

In plain words
What is it for?
Use it to enforce architecture, domain-driven design, testing, change control, security, observability, performance, continuous integration, and API standards across agent work.
Why use it?
It keeps agents consistent and makes them stop when required formats, checks, or risk controls cannot be followed.

Cursor rule

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/bogdaniel/aegis-codex/00-overview
Clone the repo
git clone --depth 1 https://github.com/bogdaniel/aegis-codex
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 624 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00624
Opus 5 $0.00000 $0.00312
Sonnet 5 $0.00000 $0.00125
Haiku 4.5 $0.00000 $0.00062

Measured 2d ago against content hash 5fb7d5b89fa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

00-overview 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.

rules/agents/00-overview.mdc · 40 lines

What it actually says

[SOURCE OF TRUTH]

  • Editable source: rules/agents/00-overview.mdc
  • Generated/consumed copy: .cursor/rules/agents/00-overview.mdc (keep references intact)

[INTENT]

  • Define shared agent rules, responsibilities, and blocking compliance criteria that apply to all core agents.

[APPLICABILITY]

  • Applies to all core agents (@architect, @implementer, @code-reviewer, @test-engineer, @security-auditor, @supervisor, @orchestrator) in all contexts; non-negotiable unless a valid risk override per .cursor/rules/3G-risk-overrides.mdc is explicitly invoked.

[CROSS-REFERENCES]

  • Architecture/DDD: .cursor/rules/36-architecture.mdc, .cursor/rules/44-ddd.mdc (binding)
  • Testing/change-discipline: .cursor/rules/31-testing.mdc, .cursor/rules/23-change-control.mdc (binding)
  • Risk overrides: .cursor/rules/3G-risk-overrides.mdc (explicit overrides only)

[AGENTS OVERVIEW]

  • All agents: enforce verification artifact; respect security/testing/observability/performance/CI/API standards; fail closed if format cannot be honored.
  • MANDATORY: All agents MUST treat .cursor/rules/36-architecture.mdc, .cursor/rules/44-ddd.mdc, and relevant 50-lang-*.mdc as hard constraints (not suggestions).
  • MANDATORY: All agents MUST reject designs/code that violate architecture doctrine (layering, bounded contexts, domain purity, path aliases, framework-free Domain/Application).
  • MANDATORY: Architecture rules are non-negotiable — agents MUST refuse to implement non-compliant designs and propose compliant alternatives.
  • MANDATORY: All agents MUST also enforce the change-discipline cluster (.cursor/rules/23-change-control.mdc, .cursor/rules/45-bugfix-protocol.mdc, .cursor/rules/46-regression-discipline.mdc, .cursor/rules/47-diff-discipline.mdc, .cursor/rules/48-doc-sync.mdc, .cursor/rules/35-api-lifecycle.mdc) as binding; violations are blocking unless a valid risk override per .cursor/rules/3G-risk-overrides.mdc is in effect.
  • MANDATORY: Risk overrides follow .cursor/rules/3G-risk-overrides.mdc exclusively; do not duplicate override semantics elsewhere.
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 · 40 lines · 0 tokens per session scan A 5fb7d5b89fa6

Subscribe to this mod's changes

00-overview is a cursor rule published in the GitHub repository bogdaniel/aegis-codex (2 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 624 tokens. 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.