AGENTS.md@.agents/skills/senpi-qaA
AGENTS.md@.agents/skills/senpi-qa from code-yeongyu/senpi is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add code-yeongyu/senpi/.agents/skills/senpi-qa/AGENTS.md@git:20260831.a99450dPins git:20260831.a99450d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- code-yeongyu/senpi
- Path
.agents/skills/senpi-qa/AGENTS.md- Versions recorded
- 2
- Latest version
- git:20260831.a99450d, committed Aug 31, 2026
- First version recorded
- Aug 24, 2026
- Size
- 3,716 bytes
- Repository stars
- 486
- License
- MIT
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
# .agents/skills/senpi-qa
Manual QA harness for the senpi coding agent, driven from source in isolated sandboxes. `SKILL.md` is the operating manual (channels, golden rules, evidence contract); root `AGENTS.md` owns when QA is mandatory. This file maps the ~107-script codebase behind them.
## STRUCTURE
```text
SKILL.md Channel manual; start here to run QA
scripts/*.mjs (32) Top-level drivers (rpc-drive, tui-smoke,
mock-loop, cli-smoke, pty-drive) + focused QA
scripts/lib/ (42) Shared harness; common.mjs is the foundation
scripts/lib/*.test.mjs (4) node:test units for lib helpers
scripts/scenarios/ (30 + helpers) One-off runners; -qa checks, -repro bugs
scripts/scenarios/cursor-exec-lifecycle/ HTTP/2 + protobuf Cursor wire helpers
scripts/scenarios/cursor-oauth-catalog-refresh/setup.ts Only TypeScript here; runs via tsx
scripts/probes/cursor-cli/ (3) Cursor CLI canaries/probes
references/ rpc-protocol, tui-driving, mock-loop,
credential-injection, env-vars
…Read the whole file at its exact version.
How to install
mdr add code-yeongyu/senpi/.agents/skills/senpi-qa/AGENTS.md@sha256:aea2e345f5f86e4dThe line at the top of this page pins the label git:20260831.a99450d, 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_vukq64bhxvp5mcnb)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 24, 2026 and Aug 31, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260831.a99450d latest | 2026-08-31 | a99450d | 3,716 B | A | view · diff |
| git:20260824.0549249 | 2026-08-24 | 0549249 | 3,717 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (3716 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
code-yeongyu/senpi · 486 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vukq64bhxvp5mcnb GET https://markdownregistry.com/api/v1/resolve?ref=code-yeongyu/senpi/.agents/skills/senpi-qa/AGENTS.md GET https://markdownregistry.com/api/v1/blob/aea2e345f5f86e4da31b13248e254b972f3cc4263367d446dc223806dfce3928
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: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.