researchforge-run

researchforge-run is a cursor rule for coding agents from forger-labs-hq/researchforge. It costs 0 tokens per session (541 once invoked), scanned A, original, Apache-2.0.

An execution rule for ResearchForge, a tool that runs repository experiments through an initial screening stage and then a full benchmark. It can also resume an interrupted run.

In plain words
What is it for?
Running approved experiment plans, comparing candidate changes with a baseline, monitoring progress, and continuing interrupted runs.
Why use it?
It provides a controlled process for comparing changes and records failures or constraint violations instead of hiding them.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/forger-labs-hq/researchforge/researchforge-run
Clone the repo
git clone --depth 1 https://github.com/forger-labs-hq/researchforge

Wrote 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.

agentmods badge for researchforge-run

README.md
[![agentmods](https://agentmods.dev/badge/rules/forger-labs-hq/researchforge/researchforge-run.svg)](https://agentmods.dev/rules/forger-labs-hq/researchforge/researchforge-run)
Your own site
<a href="https://agentmods.dev/rules/forger-labs-hq/researchforge/researchforge-run"><img src="https://agentmods.dev/badge/rules/forger-labs-hq/researchforge/researchforge-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 541 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00541
Opus 5 $0.00000 $0.00270
Sonnet 5 $0.00000 $0.00108
Haiku 4.5 $0.00000 $0.00054

Measured 5d ago against content hash 2d8d99ca53f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

researchforge-run 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 5d 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.

src/researchforge/cursor/rules/researchforge-run.mdc · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the experiment funnel

Running requires an approved plan — the engine refuses unapproved runs. If approval is missing, go back to the researchforge-plan rule; never look for a way around the gate.

researchforge experiment run <plan-id> --json

What the engine does (so you can narrate it honestly):

  • each attempt runs in its own detached git worktree with the contract's resource limits; the user's checkout is never touched;
  • a screening baseline is measured with the screening command first, so screening results are compared like-for-like;
  • experiments run one at a time: screening → survivors go to the full benchmark;
  • failures and constraint violations are recorded, not retried silently.

This can take a while (the plan's approval showed worst-case wall time). experiment run auto-starts a background live monitor when available and prints Live monitor: <url>always relay that URL to the user so they can watch stages complete in real time while you narrate results in chat (researchforge serve --status re-prints it; the monitor needs pip install "researchforge[serve]"). If the process is interrupted or times out:

researchforge experiment resume <run-id> --json

If the user does not want to continue an interrupted run, discard it so a fresh batch starts clean (ask them first — this cancels unfinished experiments, though finished results are kept):

researchforge experiment abandon <run-id>

When the run finishes, report per-experiment outcomes from the JSON — status, stage reached, and measured metrics. Screening numbers are screening numbers: never present them as full-benchmark or validated results. Then continue with the researchforge-results rule.

Rules

  • The Python engine is the boundary: never work around a validation error, a protected path, or an approval gate — fix the artifact or ask the user.
  • Approvals belong to the user: never pass --yes or type a confirmation unless the user explicitly approved that step in this conversation.
  • Ground every summary in stored data: quote only numbers returned by --json output or files under .researchforge/ — never invent metrics.

Read the full file on GitHub · 60 lines

Changes

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.

  1. 5d ago First seen · 60 lines · 0 tokens per session scan A 2d8d99ca53f0

Subscribe to this mod's changes

researchforge-run is a cursor rule published in the GitHub repository forger-labs-hq/researchforge (7 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 541 tokens. 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.

Related

Other cursor rules, from other repositories