OpenAI input safety and token readiness brief
Use “OpenAI input safety and token readiness brief” in Recued. It provides a read-only OpenAI safety workflow.
How it works
Inspect the data fetches, transforms, gates, and output this recipe runs.
Process (6 steps)
input_tokens
recued-core.openai.response_input_token.count
Count response input token on openai
moderation
recued-core.openai.moderation.create
Create moderation on openai
moderation_results
default
Apply default
result_count
count
Count items in moderation results
moderation_table
to_table
Format results as a data table
card
to_summary
Format results as a summary card
▼
Output
summary
card
table
moderation_table
Settings
Configurable at install. Defaults shown — change them anytime in Recued.
input text
setting
=
instructions
setting
=
Evaluate this input for a governed assistant workflow.
response model
setting
=
gpt-5.5
moderation model
setting
=
omni-moderation-latest
Uses (2 operations)
Pack operation
Count response input token on openai
recued-core.openai.response_input_token.count
Pack operation
Create moderation on openai
recued-core.openai.moderation.create
Trust & control
What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.