hookdeckhookdeck/outpost/.cursor/rules/agent-evaluation-authoring.mdc

outpost / rules

Cursor rule1.1k starsChanged 5 months agoApache-2.0View on GitHub

Authoring standards for docs/agent-evaluation (no eval leakage in user turns)

Oct 19, 2026Serverless mode: run reactors, reducers and Arc applications on serverless platforms with a turnkey switch — Cratis/Chronicle0 reactions · 6 comments
Oct 5, 2026Deadline gate on v1.6.0: write fence, webhook-only, no redirects (703-s13) — Ryushi-MB/outpost0 reactions
Oct 1, 2026Operator events list endpoints advertise filters and paging they silently ignore — hookdeck/evals0 reactions
Oct 1, 2026Outpost answers 502 for an unknown operator event destination id — hookdeck/evals0 reactions
May 10, 2025weekly links — Yuyz0112/koala-oss-app0 reactions · 2 comments

On Bluesky · 3

May 6, 2025🟦 Introducing Outpost — open-source outbound webhooks & event destinations infrastructure from Hookdeck (us). Scalable, reliable, and… — @hookdeck.com9 likes and reposts · 1 reply
May 6, 2025Ok, this (despite still being in its early stages) makes me happy: github.com/hookdeck/out... . @hookdeck.com I don’t remember why I signed… — @thearchivalone.bsky.social2 likes and reposts
May 20, 2025Details: github.com/hookdeck/ou... Project: github.com/hookdeck/ou... — @hookdeck.com1 likes and repost

On Hacker News · 1

May 6, 2025Show HN: Outpost – OSS infra for outbound webhooks and event destinations67 points · 8 comments

Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,144 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- hookdeck-outpost-docs-formatSkill

The file

We split this agent-evaluation-authoring.mdc into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
When editing anything under docs/agent-evaluation/, read and follow docs/agent-evaluation/AGENTS.md.
line 6
Very specific:
Put rubric detail in ## Success criteria / Intent / Failure modes, not in the user quote.
line 12

≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

agent-evaluation-authoring.mdc

---
description: Authoring standards for docs/agent-evaluation (no eval leakage in user turns)
globs: docs/agent-evaluation/**/*
---

When editing anything under `docs/agent-evaluation/`, read and follow **`docs/agent-evaluation/AGENTS.md`**.

**Quick guardrails for `scenarios/*.md`:**

- **`### Turn N — User`** blockquotes = in-character **product engineer** speech only.
- **Never** in user lines: `Option 1/2/3`, `Turn 0`, `scenario`, `eval`, `success criteria`, `scoreScenario`, references to “the prompt/instructions you already have” or named template sections.
- Put rubric detail in **`## Success criteria`** / **Intent** / **Failure modes**, not in the user quote.

Full checklist and rationale: **`docs/agent-evaluation/AGENTS.md`**.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free