file-op
Execute FileOpsREQ protocol requests. Handles autoflow domain ops for .ccb/ state management.
Best for Autoflow plan managementWorks with GitHub
⌘source
- author
@bfly123- language
- Python
★2.4kstars
228forks
Apr 30, 2026
✦overview.md
Key Features
- ·Executes FileOpsREQ protocol
- ·Validates JSON schema
- ·Manages .ccb state files
- ·Handles autoflow plan init
Use Cases
- →Initialize a new autoflow plan with state files
- →Execute a sequence of file operations from a request
- →Preflight check current state before continuing
Best for
- ✓Autoflow plan management
- ✓State file operations
Not ideal for
- !General file manipulation outside protocol
FAQs
name
file-op
description
Execute FileOpsREQ protocol requests. Handles autoflow domain ops for .ccb/ state management.
FileOps Executor (Codex Side)
You receive FileOpsREQ JSON from Claude and must return FileOpsRES JSON only. No markdown, no prose.
Protocol Reference
See ~/.claude/skills/docs/protocol.md for full FileOpsREQ/FileOpsRES schema.
Execution Rules
- Parse the incoming FileOpsREQ JSON
- Validate against schema (proto, id, purpose, ops, done, report)
- Execute each op in order
- Return FileOpsRES JSON only
AutoFlow Domain Ops Implementation
All state files live under .ccb/ directory relative to repo root.
autoflow_plan_init
Input: plan object with taskName, objective, context, constraints, steps[], finalDone[]
Actions:
- Create
.ccb/directory if not exists - Build
state.jsonfrom plan:{ "taskName": plan.taskName, "objective": plan.objective, "context": plan.context, "constraints": plan.constraints, "current": { "type": "step", "stepIndex": 1, "subIndex": null }, "steps": [ { "index": i+1, "title": title, "status": "todo" (first="doing"), "attempts": 0, "substeps": [] } ], "finalDone": plan.finalDone } - Write
.ccb/state.json - Generate
.ccb/todo.mdfrom state (see formats.md)
$install
1-click copynpx skills add bfly123/claude_codex_bridge --skill file-opSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.