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/GuoCheng24/breakthrough-harnessWrote 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/guocheng24/breakthrough-harness/breakthrough-loop)<a href="https://agentmods.dev/rules/guocheng24/breakthrough-harness/breakthrough-loop"><img src="https://agentmods.dev/badge/rules/guocheng24/breakthrough-harness/breakthrough-loop/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/guocheng24/breakthrough-harness/breakthrough-loop"><img src="https://agentmods.dev/badge/rules/guocheng24/breakthrough-harness/breakthrough-loop.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 | $0.00400 | $0.00400 |
| Opus 5.5 | $0.00160 | $0.00160 |
| Sonnet 5.5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
breakthrough-loop 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
Breakthrough-loop discipline (drop into .cursor/rules/)
Full methodology: https://github.com/GuoCheng24/breakthrough-harness
When running research experiments in this project:
- Triage the target first: cheap scoring function + existing groundwork + externally recognisable win + an oracle-ceiling/trivial-baseline gap worth mining (measure before round 1). Any missing -> flag it and stop.
- Build the harness before the method: single evaluation entry point; null models scored first and pinned to the floor; metric conventions pinned (double-report if the published one differs); calibration and evaluation data physically separated - tuning touches calibration only.
- Reproduce a published baseline number before trusting ours; an unmatched baseline means the recipe has unread layers (optimizer, loss, metric convention, operator).
- Loop: 10-30 variants/round each with a one-line reason it might win; sanity-check before entry; executors only call the entry point, never write method code inline; select on calibration; confirm top-k held-out. Unreproduced gains do not exist; report confirmations with a paired error bar, budget held-out accesses. Persist numbers to disk, then write.
- Claim polarity: the main sentence of any result is constructive ("we propose X, it solves Y, number Z"); audits and negatives are supporting material, never the headline.
- Verify every new guard by deliberately breaking what it watches, and confirm it fails for the right reason.
- Stop conditions: a well-scoring null model or any firing anti-cheat check freezes all conclusions until the harness is repaired; when candidates stop carrying new reasons, record the ceiling number and escalate to a more ambitious target class instead of continuing to sweep.
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 · 33 lines · 400 tokens per session scan A 1e328da1e04d
breakthrough-loop is a cursor rule published in the GitHub repository GuoCheng24/breakthrough-harness (1 stars, last pushed 23d ago), licensed MIT. It adds 400 tokens to every session, about $0.0016 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
project
Core project context for ai-context-kit.
project
Project conventions - canonical source is AGENTS.md.
core
The engineering contract for this repo lives in AGENTS.md (auto-loaded). Follow it. This rule only adds Cursor-specific behavior so the contract is not duplicated token-for-token on every request.
debugging
Debugging discipline. Apply when investigating a bug, test failure, or unexpected behavior.
orchestrator-main
Rules for the main orchestrator agent in multi-agent workflows.
main
Core coding standards enforced on all source files.