Tooluck logoTooluck
SKILL.md

agent-operated-workflows

Agent skill frommvschwarz/openrig

Use when a bounded real-world procedure has a deterministic happy path but brownfield, variable, or partially knowable state; when an operation must resume from verified evidence; or when deciding whether agent judgment or ordinary code should own a procedure's control loop.

How to install agent-operated-workflows

install agent-operated-workflows
# install the openrig pack with the skills CLI
npx skills add mvschwarz/openrig

# or add only this skill to Claude Code: copy the folder

packages/daemon/assets/plugins/openrig-core/skills/agent-operated-workflows/

# into

~/.claude/skills/agent-operated-workflows/ (all projects)

.claude/skills/agent-operated-workflows/ (one project)

packages/daemon/assets/plugins/openrig-core/skills/agent-operated-workflows/SKILL.md

Apache-2.0Full file
1# Agent-Operated Workflows
2
3An **Agent-Operated Workflow** is a bounded procedure whose control loop belongs to an agent. The
4agent observes, interprets, sequences bounded actions, verifies their effects, adapts, and escalates
5genuine ambiguity. Deterministic code remains the exact substrate; it does not pretend to understand
6every state of a brownfield world.
7
8## Name the architecture before using it
9
10- **AI-enabled software:** application code owns the control loop and calls a model as one capability.
11- **Agent-Operated Workflow:** an agent owns one bounded procedure with a start and stop condition.
12- **Agent-Operated Software:** an OpenRig agent or rig participates in an ongoing application's live
13 backend or control loop. It may run many workflows; see `agent-operated-software`.
14
15Calling a model is not enough. A deterministic program that consults a model still owns its loop.
16
17## Decide whether the agent earns the loop
18
19Use an agent when the happy path is deterministic but the environment is brownfield, variable,
20partially knowable, or disproportionately expensive to model exhaustively. The judgment is in
21discovering what is true and choosing the next safe act.
22
23Prefer ordinary code when the state space is closed and code is simpler and more reliable than
24judgment. A parser, fixed data transformation, or fully enumerated state machine does not become
25better because an agent drives it.
26
27## Keep ownership explicit
28
29| Owner | Responsibility |
30|---|---|
31…

Excerpt shown under the repository's Apache-2.0 license.

More skills in openrig

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates