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/evilfreelancer/zaezd/implementation-ordergit clone --depth 1 https://github.com/EvilFreelancer/zaezdWhat 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 | $0.01050 |
| Opus 5 | $0.00000 | $0.00525 |
| Sonnet 5 | $0.00000 | $0.00210 |
| Haiku 4.5 | $0.00000 | $0.00105 |
Grade A, and why
implementation-order 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation order: inner layers first
Build the cake from the inside out. A unit may be written only when everything it depends on already exists and is green. This keeps every layer testable without mocks and stops the classic hackathon failure where a beautiful screen sits on top of arithmetic nobody verified.
The order
L0. Pure domain core, src/composer/. No imports outside the file's own layer, no I/O,
no clock, no network.
types.ts-TripRequest,TripResult,TripPackage,EventCard,Leg,HotelOffer,CheckoutLink,CoverageNote,SkippedNote. The file grows feature by feature; it is never published whole in the first commit.dates.ts- check-in day, check-out day, night count.selection.ts- candidate events, with the reference date passed in as an argument.feasibility.ts- arrival buffer, departure after the event, unknown start time.pricing.ts- total participation price and budget breakdown. It receives an already marked set of working days; reading isDayOff is L2, not L0.hotels.ts- hotel ranking: by distance when the venue was geocoded precisely, otherwise by price and rating with the distance block suppressed.packages.ts- the three selection rules and their collapse to fewer cards. It chooses among combinations that L3 already assembled; building the cartesian product is L3.checkout-labels.ts- the purekindto button-label table.
L1. Sources, src/sources/. Protocol and normalization, one module per concern.
types.ts- normalized shapes the rest of the code sees.normalize.ts- raw payload (unknown) to domain types, plus forgiving input coercion.cache.ts- keyed in-memory cache with per-source TTL, replay fromfixtures/.confcal.ts- session handling, one concurrent call, automatic re-initialize.tutu.ts- sessionless client over the four tools actually used.
L2. Enrichment, src/enrich/. Each one a function with a timeout and a fallback,
independent of the others.
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 · 87 lines · 0 tokens per session scan A a4f4ace72427
implementation-order is a cursor rule published in the GitHub repository EvilFreelancer/zaezd (1 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,050 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
swift-development
Swift development: SwiftUI, Combine, async/await, iOS patterns, and Apple platform conventions.
cursorrules
When the user asks about social media, use social-media-ai-mcp tools: schedulepost, generatehashtags, analyzeengagement, plancontentcalendar, getaudienceinsights.
cursorrules
This is an MCP (Model Context Protocol) server that provides Notion integration tools and AI agent workflows. Built with TypeScript, using the MCP SDK for server implementation.
lighter-safety
Safety contract for the Lighter MCP server. Apply whenever a lighter tool is invoked.
commits
Conventional Commits standards for clear, semantic commit messages.
nix-security
Nix Security and Sandboxing.