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.
git clone --depth 1 https://github.com/EvilFreelancer/zaezdWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/evilfreelancer/zaezd/workflow)<a href="https://agentmods.dev/rules/evilfreelancer/zaezd/workflow"><img src="https://agentmods.dev/badge/rules/evilfreelancer/zaezd/workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/evilfreelancer/zaezd/workflow"><img src="https://agentmods.dev/badge/rules/evilfreelancer/zaezd/workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01612 | $0.01612 |
| Opus 5.5 | $0.00645 | $0.00645 |
| Sonnet 5.5 | $0.00322 | $0.00322 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
workflow 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: specification first, then tests, then code
Zaezd is delivered BDD-style. The executable Gherkin specification is the contract,
the unit tests are the safety net, the implementation comes last. Tests and specs are
the long-term memory of this project: if a behavior is not described in
features/**/*.feature, it does not exist.
New behavior (feature)
Triggered by "фича", "feature", "добавить", "implement", "add a use case". Do not skip a step and do not reorder them.
- Write the Gherkin specification first.
Add or extend a
.featurefile underfeatures/. Describe the observable outcome in business language, following @bdd-specs.mdc. This happens before any test file and before any production code. - Make the specification executable.
Add the missing step definitions under
features/steps/. Runnpm run bdd. The scenario must now fail for a real reason (missing behavior), not because a step is undefined. A specification that cannot run is not a specification. - Drop to unit tests for the pure logic.
For every deterministic rule the scenario depends on (dates, feasibility, pricing,
package selection, normalization, cache keys) add a failing unit test under
tests/, per @testing.mdc. - Implement, lowest layer first. Follow @implementation-order.mdc and @architecture.mdc. One unit at a time. Never write a higher layer before the layer under it is green.
- Green the unit tests, then the scenario.
npm test, thennpm run bdd. In that order: a green scenario over red units means the units are undertested. - Run the full gate.
npm run verify(rules check, typecheck of both the Node and the browser tree, lint, the browser build, bdd, unit tests). Everything green, no exceptions. The browser tree is compiled before the specifications because one of them asks the server for the compiledboot.js, and on a clean clone that file does not exist yet. - Update the documentation in the same change.
README,
docs/user-guide.md,docs/architecture.md,docs/decisions.md. Never document a capability that does not exist in the code: the repository is graded by an AI reviewer that compares documentation against the code, and a mismatch costs more than a missing feature. - Rules Sync (see below).
- Report using the structure below.
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.
- 1mo ago First seen · 141 lines · 1,612 tokens per session scan A c01379c2c6b7
workflow is a cursor rule published in the GitHub repository EvilFreelancer/zaezd (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,612 tokens to every session, about $0.0064 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
20-tests
Testing rules — applies when editing tests or code under test.
python-code-validator
Validate generated Python at every step, not once at the end.
qa-agent
QA workflow for reviewing stories, designing tests, and reporting verified defects.
testing
Testpflicht für nicht-trivialen Code.
rule_main
Core non-negotiable engineering checks.