AGENTS.md@experiments/runs/2026-05-25_18-27-53_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_glm-5-1-2A

This file is byte-identical to the first copy the registry indexed, one of 45 indexed copies. Same content hash, so the same checks give both the same grade.

AGENTS.md@experiments/runs/2026-05-25_18-27-53_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_glm-5-1-2 from marcoemrich/agentic_coding_lab is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add marcoemrich/agentic_coding_lab/experiments/runs/2026-05-25_18-27-53_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_glm-5-1-2/AGENTS.md@git:20260525.0a75e2c

Pins git:20260525.0a75e2c in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
marcoemrich/agentic_coding_lab
Path
experiments/runs/2026-05-25_18-27-53_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_glm-5-1-2/AGENTS.md
Versions recorded
1
Latest version
git:20260525.0a75e2c, committed May 25, 2026
Size
6,535 bytes
Repository stars
37
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

# Test-Driven Development (TDD) Rules

## CRITICAL: Skill Usage is MANDATORY

**YOU MUST USE THE SPECIALIZED TDD SKILLS FOR EVERY TDD TASK.**

Do NOT perform TDD phases without invoking the appropriate skill. The skills enforce discipline and prevent common mistakes.

### Before Starting Any TDD Work - Complete This Checklist:

- [ ] Have I been asked to implement something using TDD?
- [ ] Am I about to write tests or implementation code?
- [ ] **STOP** - Use the `skill` tool to invoke the appropriate TDD skill
- [ ] NEVER write tests or code directly - ALWAYS use skills

### Which Skill to Use:

| Phase | Skill Name | Invoke With |
|-------|-----------|-------------|
| Test List | `test-list` | `skill({ name: "test-list" })` |
| Red Phase | `red` | `skill({ name: "red" })` |
| Green Phase | `green` | `skill({ name: "green" })` |
| Refactor Phase | `refactor` | `skill({ name: "refactor" })` |

**If you find yourself writing test code or implementation code without invoking a skill first, you are doing it WRONG.**

## Overview

This project follows strict Test-Driven Development practices using the Red-Green-Refactor cycle.

## TDD Workflow
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add marcoemrich/agentic_coding_lab/experiments/runs/2026-05-25_18-27-53_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_glm-5-1-2/AGENTS.md@sha256:ebac288ec3cc0fe8

The line at the top of this page pins the label git:20260525.0a75e2c, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_tuscvqagfuiqczld.svg)](https://markdownregistry.com/a/art_tuscvqagfuiqczld)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on May 25, 2026.

versioncommittedcommitsizeaudit
git:20260525.0a75e2c latest2026-05-25 0a75e2c 6,535 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (6535 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

GitHub

marcoemrich/agentic_coding_lab · 37 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tuscvqagfuiqczld
GET https://markdownregistry.com/api/v1/resolve?ref=marcoemrich/agentic_coding_lab/experiments/runs/2026-05-25_18-27-53_claim-office-example-mapping_v5.1-testlist-scope-fix-oc_glm-5-1-2/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/ebac288ec3cc0fe83c6ca2087f7925b232a6035c541d2087c69804051fe3422f

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.

More from marcoemrich/agentic_coding_lab

build-overview SKILL.md skill
marcoemrich/agentic_coding_lab · .claude/skills/build-overview/SKILL.md · Generates an experiment-overview snapshot of all research questions under research/reports/. Invoke when a new…
git:20261011.b7a9cef · audit A · 37 stars
exact-coding-baseline-export SKILL.md skill
marcoemrich/agentic_coding_lab · .claude/skills/exact-coding-baseline-export/SKILL.md · Mint a new YYYY-MM-DD-exact-coding-baseline snapshot under research/workflow-dev/export/. Detects the current best…
git:20261001.51935f9 · audit A · 37 stars
reanalyze SKILL.md skill
marcoemrich/agentic_coding_lab · .claude/skills/reanalyze/SKILL.md · Re-run the analysis pipeline on all runs matching an RQ, reaggregate metrics, and propose findings updates against the…
git:20261011.b7a9cef · audit A · 37 stars
run-rq SKILL.md skill
marcoemrich/agentic_coding_lab · .claude/skills/run-rq/SKILL.md · Use this skill to drive a research question (RQ) end-to-end: validate the RQ README, generate a fill batch-plan, start…
git:20261014.b8e5e79 · audit A · 37 stars
build-overview SKILL.md skill
marcoemrich/agentic_coding_lab · .opencode/skills/build-overview/SKILL.md · Generates an experiment-overview snapshot of all research questions under research/reports/. Invoke when a new…
git:20261011.b7a9cef · audit A · 37 stars
exact-coding-baseline-export SKILL.md skill
marcoemrich/agentic_coding_lab · .opencode/skills/exact-coding-baseline-export/SKILL.md · Mint a new YYYY-MM-DD-exact-coding-baseline snapshot under research/workflow-dev/export/. Detects the current best…
git:20261001.69926be · audit A · 37 stars
reanalyze SKILL.md skill
marcoemrich/agentic_coding_lab · .opencode/skills/reanalyze/SKILL.md · Re-run the analysis pipeline on all runs matching an RQ, reaggregate metrics, and propose findings updates against the…
git:20261001.18c28e0 · audit A · 37 stars
run-rq SKILL.md skill
marcoemrich/agentic_coding_lab · .opencode/skills/run-rq/SKILL.md · Use this skill to drive a research question (RQ) end-to-end: validate the RQ README, generate a fill batch-plan, start…
git:20261011.b7a9cef · audit A · 37 stars
CLAUDE.md CLAUDE.md file
marcoemrich/agentic_coding_lab · CLAUDE.md
git:20261014.a2b7ca5 · audit A · 37 stars
AGENTS.md@experiments/runs/2026-05-25_06-19-06_claim-office-prose_v1-oneshot-oc_opus-4-7-portkey/.opencode AGENTS.md file
marcoemrich/agentic_coding_lab · experiments/runs/2026-05-25_06-19-06_claim-office-prose_v1-oneshot-oc_opus-4-7-portkey/.opencode/AGENTS.md
git:20260525.03fa58e · audit A · 37 stars
AGENTS.md@experiments/runs/2026-05-25_06-19-06_claim-office-prose_v1-oneshot-oc_opus-4-7-portkey AGENTS.md file
marcoemrich/agentic_coding_lab · experiments/runs/2026-05-25_06-19-06_claim-office-prose_v1-oneshot-oc_opus-4-7-portkey/AGENTS.md
git:20260525.03fa58e · audit A · 37 stars
AGENTS.md@experiments/runs/2026-05-25_06-43-28_claim-office-prose_v1-oneshot-oc_opus-4-7-portkey/.opencode AGENTS.md file
marcoemrich/agentic_coding_lab · experiments/runs/2026-05-25_06-43-28_claim-office-prose_v1-oneshot-oc_opus-4-7-portkey/.opencode/AGENTS.md
git:20260525.a1239d0 · audit A · 37 stars

Every file in marcoemrich/agentic_coding_lab

Browse by kind, by grade A, or by owner.