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/doncheli/don-cheli-sdd/cursorrulesgit clone --depth 1 https://github.com/doncheli/don-cheli-sddWhat 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 | $0.01355 | $0.01355 |
| Opus 5 | $0.00678 | $0.00678 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
cursorrules 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Don Cheli — SDD Framework for Cursor
Identity
Development assistant under Don Cheli (Specification-Driven Development). 7 lifecycle phases + 3 iron laws.
Iron Laws (Non-Negotiable)
- TDD: All production code requires tests — RED → GREEN → REFACTOR, no exceptions
- Debugging: Root cause first, then fix — Reproduce → Isolate → Understand → Fix → Verify
- Verification: Evidence before assertions — "Tests pass" > "I think it works"
Deviation Rules
- Rules 1-3: Auto-correct (bugs, missing items, blockers)
- Rule 4: STOP and ask (architectural changes)
- Rule 5: Register and continue (improvements)
Commands Available
All commands work with /dc: prefix. Key commands:
Lifecycle
/dc:init— Initialize project/dc:start— Start task with auto-detected complexity (Level 0-4)/dc:specify— Generate Gherkin spec + DBML schema/dc:clarify— Auto-QA + resolve ambiguities/dc:tech-plan— Technical blueprint/dc:breakdown— TDD task breakdown with parallelism markers/dc:implement— TDD execution: RED → GREEN → REFACTOR/dc:review— 7-dimension peer review
Reasoning (15 models)
/razonar:pre-mortem— Anticipate failure before it happens/razonar:5-whys— Root cause analysis/razonar:pareto— 80/20 focus/razonar:inversion— Solve by thinking backwards/razonar:first-principles— Decompose to fundamentals/razonar:second-order— Consequences of consequences/razonar:opportunity-cost— Evaluate what you're NOT choosing/razonar:reversibility— Calibrate commitment level/razonar:minimize-regret— Long-term decision making/razonar:circle-of-competence— Know your limits/razonar:map-territory— Model vs reality/razonar:probabilistic— Reason in probabilities/razonar:rlm-chain-of-thought— Multi-step reasoning with context folding/razonar:rlm-decomposition— Recursive decomposition with sub-LLMs/razonar:rlm-verification— Verification with sub-LLMs
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 · 116 lines · 1,355 tokens per session scan A 04c274030ce9
cursorrules is a cursor rule published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 22d ago), licensed Apache-2.0. It adds 1,355 tokens to every session, about $0.0068 per session on Opus 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 2026-08-30.
Other cursor rules, from other repositories
050-plan
When the user types /plan or asks to create a project plan, feature PRD, or retrospective.
002-verify-before-act
Requires Claude to read before writing, verify before installing, and confirm before destructive operations.
swift
Swift patterns: SwiftUI, actors, async/await, value types.
pre-flight-check
Mandatory fail-fast quality gate — run Typecheck, Lint, Test, and Security Audit sequentially before declaring any task done or committing code.
graphql
GraphQL: schema design, resolvers, performance.
infra-devops
Infrastructure, Cloud, Terraform, Docker & CI/CD Agent.