osop-log
Generate OSOP session log — creates .osop workflow and .osoplog.yaml execution record
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/archie0125/osop-logOSOP Session Logger
You just completed a task. Now produce a structured session log.
What to create
sessions/YYYY-MM-DD-<short-desc>.osop— workflow definitionsessions/YYYY-MM-DD-<short-desc>.osoplog.yaml— execution record
Create the sessions/ directory if it doesn't exist.
Task description
$ARGUMENTS
.osop format
osop_version: "1.0"
id: "session-<short-description>"
name: "<What you did>"
description: "<1-2 sentence summary>"
version: "1.0.0"
tags: [claude-code, <relevant-tags>]
nodes:
- id: "<step-id>"
type: "<node-type>" # human, agent, mcp, cli, api, cicd, git, db, docker, infra, system, event, gateway, data, company, department
subtype: "<subtype>" # Optional: llm, explore, plan, worker, tool, test, commit, rest, etc.
name: "<Step Name>"
description: "<What this step does>"
security:
risk_level: "<low|medium|high|critical>"
edges:
- from: "<step-a>"
to: "<step-b>"
mode: "sequential" # sequential, parallel, conditional, fallback, error, spawn, etc.
.osoplog.yaml format
osoplog_version: "1.0"
run_id: "<generate-uuid>"
workflow_id: "<matches .osop id>"
mode: "live"
status: "COMPLETED"
trigger:
type: "manual"
actor: "user"
timestamp: "<ISO timestamp>"
started_at: "<ISO timestamp>"
ended_at: "<ISO timestamp>"
duration_ms: <total ms>
runtime:
agent: "claude-code"
model: "<current model>"
node_records:
- node_id: "<step-id>"
node_type: "<type>"
attempt: 1
status: "COMPLETED"
started_at: "<ISO>"
ended_at: "<ISO>"
duration_ms: <ms>
outputs:
<what you produced>
tools_used:
- { tool: "<tool-name>", calls: <n> }
reasoning:
question: "<what was decided>"
selected: "<chosen approach>"
confidence: <0.0-1.0>
result_summary: "<1-2 sentence summary>"
Node type mapping
| Action | type | subtype |
|---|---|---|
| Read/explore files | mcp | tool |
| Edit/write files | mcp | tool |
| Shell commands | cli | script |
| Run tests | cicd | test |
| Git operations | git | commit / branch / pr |
| Analyze/reason | agent | llm |
| Search codebase | mcp | tool |
| Ask user | human | input |
| User reviews | human | review |
| Spawn sub-agent | agent | explore / plan / worker |
| API calls | api | rest |
Sub-agent tracking
If you spawned sub-agents, use parent on child nodes and spawn edge:
nodes:
- id: "coordinator"
type: "agent"
subtype: "coordinator"
- id: "explore_1"
type: "agent"
subtype: "explore"
parent: "coordinator"
edges:
- from: "coordinator"
to: "explore_1"
mode: "spawn"
Important
- Be accurate about what tools were used and how many calls
- Include reasoning for non-obvious decisions
- Estimate durations based on tool call timing
- If the task failed, set status to FAILED and include error details
- View logs at https://osop-editor.vercel.app
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-archie0125-osop-log": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
osop
OSOP workflow authoring, validation, risk analysis, and self-optimization for AI agents
osop-review
Review .osop/.osoplog for security risks, permission gaps, and destructive commands
osop-optimize
Analyze .osoplog execution history to optimize workflows — finds slow steps and parallelization opportunities
osop-report
Convert .osop and .osoplog.yaml into standalone HTML report with dark mode and expandable nodes