e2e-loop SKILL.md skillA
e2e-loop from tomosia-vietnam/open-pr is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tomosia-vietnam/open-pr/e2e-loop@git:20260924.bd5b961Pins git:20260924.bd5b961 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tomosia-vietnam/open-pr
- Path
.claude/skills/e2e-loop/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260924.bd5b961, committed Sep 24, 2026
- First version recorded
- Aug 4, 2026
- Size
- 5,757 bytes
- Repository stars
- 45
- License
- MIT
Run the open-pr e2e fixture through a real review in a fresh subagent, grade it against e2e/checklist.md with a second independent subagent, diagnose each failure to the prompt file that owns it, fix, and repeat until clean or the round budget runs out. Use when changing anything under src/ and you want evidence the review still behaves, not just green unit tests.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# e2e loop The unit suite proves the prompt graph is well-formed. It cannot prove a review still comes out right. This closes that gap: run → grade → diagnose → fix → re-run, with the running and the grading done by DIFFERENT agents so neither marks its own work. Costs real money and posts to a real PR on `open-pr-test`. Never start a round the user did not ask for. ## Why subagents rather than this session A dev session already knows which defects the fixture plants and which rule was just edited. Reviewing from that context tests the session's memory, not the prompts. Each round therefore spawns fresh agents that were told nothing beyond what a real user's session gets. ## Round budget Ask for `max_rounds` if the user did not say; default **2**. Stop early when every checklist row passes, or when a round produces no NEW passing row — a loop that keeps editing without moving the score is the failure mode this skill is most likely to hit. ## Preflight 1. `scripts/check.sh <base-ref>` must be green. A red suite makes every later verdict unreadable. 2. `e2e/bootstrap.sh --pr <n> [--vendor …]` if no fixture PR is open for this round. …
Read the whole file at its exact version.
How to install
mdr add tomosia-vietnam/open-pr/e2e-loop@sha256:62bdc78a652e4358The line at the top of this page pins the label git:20260924.bd5b961, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_cc7fq7xp56je5tsv)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 4, 2026 and Sep 24, 2026, about one every 51 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260924.bd5b961 latest | 2026-09-24 | bd5b961 | 5,757 B | A | view · diff |
| git:20260804.7763fe9 | 2026-08-04 | 7763fe9 | 5,773 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5757 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
tomosia-vietnam/open-pr · 45 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cc7fq7xp56je5tsv GET https://markdownregistry.com/api/v1/resolve?ref=tomosia-vietnam/open-pr/e2e-loop GET https://markdownregistry.com/api/v1/blob/62bdc78a652e4358881388b53d5f31c59e51949890fe3e8aba606b2c182df2bb
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.