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/sandeep-alluru/agentdeltaWrote 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/sandeep-alluru/agentdelta/redline)<a href="https://agentmods.dev/rules/sandeep-alluru/agentdelta/redline"><img src="https://agentmods.dev/badge/rules/sandeep-alluru/agentdelta/redline/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/sandeep-alluru/agentdelta/redline"><img src="https://agentmods.dev/badge/rules/sandeep-alluru/agentdelta/redline.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 | $0.00510 | $0.00510 |
| Opus 5.5 | $0.00204 | $0.00204 |
| Sonnet 5.5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
redline 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.
What it actually says
redline — Cursor Rules
What this project does
Semantic diff engine for AI agent behavior. Records agent traces as JSONL, embeds steps with all-MiniLM-L6-v2, aligns two traces by cosine similarity, detects the first semantic fork point.
Module map
trace.py— data model (TraceNode, TraceEdge, AgentTrace, NodeType, EdgeType)embed.py— thread-safe sentence-transformer singleton + sliding-window alignmentdiff.py— diff_traces() → DiffResult, ForkPoint, StepDiffinstrument.py— LangChain callback + record() context managerreport.py— Rich/JSON/Markdown formatterscli.py— Click CLI (diff, inspect commands)
Invariants — never break these
- TraceNode.id is SHA-256[:16] of "{node_type}:{content}" — must stay content-addressed
- embed_trace() is idempotent — safe to call twice on the same trace
- fork_threshold=0.70 and match_threshold=0.85 are the defaults; don't change without tests
- has_regression is True iff fork_point is not None — no other state
- All embeddings come from the thread-safe _get_model() singleton in embed.py
Code style
- Python 3.10+, fully type-annotated, mypy strict mode
- Ruff lint rules: E W F I UP B S N SIM RUF PT
- No print() in library code — use rich.console.Console
- All public functions and classes must have Google-style docstrings
- Tests: pytest, CliRunner for CLI tests, no mocking of embed model (use short test traces)
When adding a new output format
- Add
to_<format>(result: DiffResult) -> strin report.py - Add format name to --format Choice in cli.py
- Add at least 2 tests in tests/test_report.py
When adding a new instrumentation adapter
- Create src/redline/instrument_.py
- Implement a context manager mirroring record() in instrument.py
- Export from init.py, add to all alphabetically
- Add tests in tests/test_instrument_.py
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 · 44 lines · 510 tokens per session scan A b1b839c095b1
redline is a cursor rule published in the GitHub repository sandeep-alluru/agentdelta (0 stars, last pushed 2mo ago), licensed MIT. It adds 510 tokens to every session, about $0.0020 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
interview-collector
Collect public AI Agent, LLM, RAG, and MCP interview experiences for agent-interview-hub.
memory-reflex
Pensyve memory reflex — the non-optional reasoning discipline for working-memory substrate.
memory-informed-longitudinal-work
Long-running multi-session work (research, eval loops, iterative benchmarks) — resume prior lessons, capture per-run outcomes, build up stable truths over time.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
context-loader
Use when starting a new substantive conversation or switching contexts — load relevant memories to prime the session with continuity.
memory-informed-debug
Use when diagnosing bugs, errors, failing tests, or crashes — consult prior debug outcomes and capture root causes in-flight.