Stub — placeholder for a concept referenced by other articles but not yet authored. Tracked as link-debt by
_system/lint.py; this file keeps the no-dangling-links invariant.
<!-- TODO: author during a /compile pass that does the cross-vendor sweep across the 6+ articles that touch this pattern. Thrice-deferred in the log (2026-04-28, 2026-05-06, 2026-05-21). -->
Intended scope: the cross-vendor markdown-as-control-plane pattern — repo-versioned plaintext
files that configure agent behavior: CLAUDE.md / AGENTS.md / SOUL.md / WORKFLOW.md /
SPEC.md / .cursorrules. Compare the role split (project vs personality vs workflow vs spec) across
vendors and argue why this is converging into an emerging standard.
Referenced from: Claude Code Best Practices, Hermes Agent
Cited by 3
- Agent Control Plane Patterns: Tickets, Loops, Specs, and Memory Files
Layered agent control-plane synthesis: tickets as durable work graph, loops as execution primitive, specs/context files…
- Claude Code Best Practices
Anthropic's guide to effective Claude Code usage: context management, verification-driven development, explore→plan→cod…
- Hermes Agent
Nous Research's CLI agent + Gateway daemon (Telegram/Discord/Slack/WhatsApp); AGENTS.md/SOUL.md context split, bounded…
Related articles
- Agent Harness Engineering
Patterns for scaffolding long-running LLM agents: environment design, progressive context disclosure, mechanical archit…
- Client-Side Agent Optimization
AgentOpt's framing of developer-controlled agent optimization (model-per-role, budget, routing) as distinct from server…
- Symphony
OpenAI's open-source agent orchestrator (March 2026): turns Linear into a control plane for Codex, per-issue workspace,…
- Ticket-Driven Agent Orchestration
The inversion that makes Symphony work: tickets as units of work (not sessions/PRs), DAG dependencies, agent-extensible…
- Claude Code Auto Mode
Claude Code permission mode using a classifier to auto-approve safe tool calls and block risky ones; middle ground betw…