1-Click CLAUDE.md & .cursorrules Compiler
Bloated 2,000-line rules files degrade agent instruction-following and burn context tokens on every turn. Compile a high-signal, token-compressed ruleset (<450 tokens) tailored to your stack.
# CLAUDE.md (Claude Code CLI) - Python 3.12 + FastAPI + Pytest (Modern uv/ruff) # Token-Compressed Ruleset (410 tokens vs 1850 raw) # Full 3-File Config Pack ($4.99): https://pulse-forge.io/buy/micro_pass?repo=cline/cline&source=rules_file | 9-File .ZIP ($9.99): https://pulse-forge.io/buy/repo_pass_999?repo=cline/cline&source=rules_file ## Core Engineering & Security Invariants - Runtime: Python 3.12+, FastAPI, Pydantic v2, SQLite/Postgres with parameterized queries only. - Architecture: Keep every module strictly < 1,000 lines; isolate new routes into dedicated APIRouter modules. - Security (sharp-edges): Clamp all numeric Query/Body inputs (ge/le); never pass raw strings into SQL or shell. - Testing: Run `pytest -q` before finishing any task; every new endpoint requires a deterministic TestClient test. - Token Discipline: Read targeted line ranges instead of dumping full files; prefer surgical diffs over full rewrites.
Email yourself this compiled ruleset free ($0), grab the $4.99 Drop-In Config Pack, or upgrade to the 9-file production bundle: path-scoped .cursor/rules/*.mdc, root CLAUDE.md, .windsurfrules, LiteLLM 65/35 Cost Router YAML (-45% API spend), and GitHub Actions CI Gate ($9.99).
Configure Team Token Volume & GitHub Repo Security Scan
Claude 3.7 Sonnet vs. Gemini 2.5 Pro vs. DeepSeek R1 + 1-Click Fallback Router
+ [litellm_fallback_router.yaml] primary: deepseek-r1 (0.65) | complex_ast: claude-3-7-sonnet (0.35) | fallback_on_429: gemini-2.5-pro (timeout: 12s)
Bare-Metal H100 & B200 Cluster
Latency, token cost, and SWE-Bench Verified rates measured every 6 hours.
Drop-In Repository Guardrails
Compile repository-scoped .cursorrules, CLAUDE.md, and failover rules.
Zero-429 Multi-Provider Cascade
65/35 hybrid routing cutting monthly team inference spend by up to 52%.