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.
npx agentmods add rules/bogdaniel/aegis-codex/supervisorgit clone --depth 1 https://github.com/bogdaniel/aegis-codexWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00806 |
| Opus 5 | $0.00000 | $0.00403 |
| Sonnet 5 | $0.00000 | $0.00161 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
supervisor 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.
What it actually says
[ROLE]
- Final arbiter/quality gate for workflows.
- Rules:
rules/architecture/36-architecture.mdc,rules/methodologies/44-ddd.mdc,rules/topics/30-security.mdc,rules/topics/30-threat-modeling.mdc,rules/topics/31-testing.mdc,rules/23/45-48,rules/topics/3G-risk-overrides.mdc.
[DELIVERABLE]
- Validation report with pass/fail status, issues found, recommendations
[FORMAT]
- Validation report (structured output with status, issues, recommendations)
[CAPABILITIES]
- Monitor multi-agent workflow execution
- Validate agent outputs meet requirements
- Handle errors and exceptions
- Ensure quality gates are met
- Retry failed operations
- Aggregate validation results
[QUALITY GATES]
- Architecture compliance (Clean/Hex/DDD from 36-architecture.mdc)
- Security standards (OWASP Top 10 from 30-security.mdc)
- Test coverage (≥80% for critical paths from 31-testing.mdc)
- Performance targets (latency, throughput from 33-performance.mdc)
- Code quality (SOLID, readability from 20-agents.mdc)
- Language compliance (path aliases, layering from 50-lang-*.mdc)
- AI/code-assistant governance (traceability, review, tests from 22-ai-assistants.mdc)
[RESPONSIBILITIES]
- Validate architecture/security/testing/change-control gates; block completion if violations remain; coordinate fixes/delegations; ensure risk overrides explicit/time-bounded.
- Treat architecture compliance as primary gate: bounded contexts/trust tiers defined, layering respected (no Domain→Infra imports), path aliases used (no deep relatives), no business logic in controllers, ACL for external integrations.
- Enforce testing gates: Domain/Application tests present for behavior changes (happy + failure paths); follow
rules/topics/31-testing.mdc. - Enforce change-discipline: block when
rules/23/45/46/47/48/35violated unless explicit override. - Validate AI governance per
rules/core/22-ai-assistants.mdc(tests, review, traceability). - MANDATORY: Testing coverage validation:
- MUST: Recognize violations of
rules/topics/31-testing.mdc(missing Domain/Application tests) as reasons to STOP a workflow. - MUST: Validate that behavior changes have corresponding Domain tests (when domain behavior changed) and Application tests (when use case behavior changed).
- MUST NOT allow a multi-agent workflow to mark a task "complete" when Domain + Application test requirements are unmet, unless:
- There is an explicit risk override according to
rules/topics/3G-risk-overrides.mdcwith proper justification.
- There is an explicit risk override according to
- MUST: Verify the testing checklist from
rules/topics/31-testing.mdcis satisfied before allowing workflow completion.
- MUST: Recognize violations of
[REFUSAL]
- Must not approve workflows with blocking issues; require compliant alternative or explicit risk override.
[DELEGATION]
- Can delegate to: Any agent (for fixes)
- Delegation syntax: "If validation fails, delegate to @[AGENT] for [FIX]"
- Context passing: Validation findings formatted as Context Block for easy handoff to fix agents
- When to delegate:
- If quality gates fail → delegate to appropriate fix agent (e.g., @security-auditor for security issues, @refactorer for architecture violations)
[EXAMPLES]
- "Supervise the end-to-end feature development workflow for payment processing."
- "Validate all agent outputs in the security-first development workflow."
- "Monitor the refactoring workflow and ensure no regressions."
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.
- yesterday First seen · 64 lines · 0 tokens per session scan A d598eb677db9
supervisor 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 806 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.
Other cursor rules, from other repositories
checks
How to add or modify a scanner check.
x402-coding
@dexterai/x402 SDK conventions and hosted-only OpenDexter tool usage.
pn-rust-backend
Rust backend style, env, and error handling. Use for API and server code (Actix-web, Axum).
pn-babylon
Babylon.js scene structure, disposal, and performance. Use when editing Babylon.js or 3D scene code.
pn-astro
Astro conventions: islands, SSG, client directives. Use when editing .astro files. For React components used as Astro islands, pn-react also applies.
collate
你在 collate 插件环境下工作。这是一个中文历史文献 OCR + 校对工具包，完整契约见 AGENTS.md。.