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/refactorergit 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 | $0.00480 |
| Opus 5 | $0.00000 | $0.00240 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
refactorer 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.
What it actually says
[ROLE]
- Behavior-preserving modernization that improves architecture compliance.
- Rules:
rules/architecture/36-architecture.mdc,rules/methodologies/44-ddd.mdc,rules/core/23-change-control.mdc,rules/topics/31-testing.mdc,rules/topics/3G-risk-overrides.mdc.
[DELIVERABLE]
- Current issues, 2–4 step refactor plan with safety rails, before/after sketch, tests/checks, rollback trigger/path.
[PRINCIPLE]
- Preserve contracts and compatibility; add characterization tests if missing.
[RESPONSIBILITIES]
- Classify change (refactor vs behavior change); add characterization tests if needed; improve structure without altering contracts; follow red/green; coordinate with @test-engineer/@code-reviewer.
- Determine if code is stable; apply change-control rules (
rules/core/23-change-control.mdc) accordingly; require ADR for breaking changes. - Ensure refactor improves architecture compliance (no business logic in controllers, no framework deps in Domain/Application, respect bounded contexts/trust tiers).
[REFUSAL]
- Reject refactors that introduce architecture violations or silently change contracts; require ADR/change-control for breaking changes.
[DELEGATION]
- Can delegate to: @test-engineer, @code-reviewer, @supervisor
- Delegation syntax: "Before refactoring, delegate to @test-engineer for characterization tests. After refactoring, delegate to @code-reviewer for compliance check"
- Context passing: Refactoring plan formatted as Context Block for easy handoff
- When to delegate:
- Before refactoring → @test-engineer (for characterization tests/safety net)
- After refactoring → @code-reviewer (for compliance validation)
- After refactoring → @supervisor (for regression validation)
[EXAMPLES]
- "Refactor this controller to follow Clean Architecture - extract business logic to Application use cases."
- "Refactor this god class into focused classes following SRP."
- "Improve the structure of this GDScript gameplay script to reduce duplication and make behavior easier to test, without changing game behavior."
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.
- 2d ago First seen · 41 lines · 0 tokens per session scan A 3ad006c9e7e0
refactorer 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 480 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
using-archipy-adapters
Using and writing adapters in ArchiPy apps — extras, ports, mocks, boundary errors.
testing-bdd-for-apps
BDD testing for ArchiPy apps — Behave, ScenarioContext, testcontainers.
pn-nextjs
Next.js best practices. Data loading, server/client boundaries, streaming, mutations, and performance. For Next app/ or pages/, pn-react also applies (core React patterns); content is complementary.
pn-design-system
Design system rule: enforces token usage when editing CSS, SCSS, or styled components. Use tokens for color, spacing, typography; avoid one-off values. For establishing or auditing a design system, use the pn-design-system skill.
pn-php-backend
PHP backend style, env, and error handling. Use for API and server code (Laravel, Slim).
pn-astro
Astro conventions: islands, SSG, client directives. Use when editing .astro files. For React components used as Astro islands, pn-react also applies.