AGENTS.md is agent-read markdown (agents) from papadopouloskyriakos/agentic-chatops.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# AGENTS.md — Claude Gateway
Entry point for any coding agent operating in this repository. The course (Google
5-Day AI Agents, Day 5) calls for a root `AGENTS.md`; this is it.
## Read first
- **`CLAUDE.md`** — operating instructions, hostnames, MCP tools, conventions (authoritative).
- **`.claude/rules/`** — infrastructure, platform-features, workflows, CI/CD rules.
- **`.claude/skills/chatops-workflow/SKILL.md`** — Phase 0→6 incident choreography.
## Spec-driven surfaces (D2 slice — IFRNLLEI01PRD-1260)
The safety-critical behaviors and component interfaces are specified under **`spec/`**
and governed by **`constitution.md`**. Before changing any file listed in a
`spec/<context>/tasks.json#files_owned`, update its `REQ-NNN` requirement and Gherkin
acceptance in the same commit (Article I + VII). Validate with:
```
python3 bootstrap-pack/scripts/validate-project-spec.py .
python3 scripts/check-spec-code-lockstep.py
```
Both run in CI (`validate_spec`), the QA suite (`test-1260-spec-driven.sh`), and
holistic-health. A change that breaks them fails the pipeline.
## What is and is not spec-regenerable
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_lg4oh3vr7ostsjpt
GET https://markdownregistry.com/api/v1/resolve?ref=papadopouloskyriakos/agentic-chatops/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/28f1cb309daa88deda7fb67a43733ca9bc60b7f580e83276c5a7ef30a2199df7
Your agent 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.
papadopouloskyriakos/agentic-chatops · bootstrap-pack/.claude/skills/specify/SKILL.md · Phase B of greenfield project bootstrap. Interview the operator to produce PROJECT.json + PROJECT.md +…
papadopouloskyriakos/agentic-chatops · bootstrap-pack/.claude/skills/tasks/SKILL.md · Phase E of greenfield project bootstrap. Atomize design.md + contracts into tasks.json with files_owned + dependencies…
papadopouloskyriakos/agentic-chatops · openclaw/skills/codegraph-lookup/SKILL.md · Query code graph database for function callers, callees, dependencies, and dead code in CubeOS and MeshSat repos.
papadopouloskyriakos/agentic-chatops · openclaw/skills/correlated-triage/SKILL.md · When multiple hosts alert simultaneously (burst), create a master YouTrack issue, run per-host triage, link children…
papadopouloskyriakos/agentic-chatops · openclaw/skills/error-propagation/SKILL.md · Structured error reporting format for triage failures — ERROR_CONTEXT format so next tier can resume without re-doing…
papadopouloskyriakos/agentic-chatops · openclaw/skills/escalate-to-claude/SKILL.md · Escalate a YouTrack issue to Claude Code (Tier 2) for CODE IMPLEMENTATION ONLY. Use ONLY when someone explicitly asks…
papadopouloskyriakos/agentic-chatops · openclaw/skills/exec-safety/SKILL.md · Blocked command list for exec tool — commands that must NEVER be executed, even if asked.
