nora actions

Actions fire after the Agent decides. Unlike Tools (which the Agent picks during a run), Actions run based on wiring: the Flow decides whether to fire, the Agent’s output decides what to pass in. Same command shape as Tools, minus parameters (Actions don’t have LLM-picked args).

Commands

Command	Description
`actions create --name <n>`	Add an Action block.
`actions update <action-id>`	Patch fields.
`actions edit <action-id>`	Open in `$EDITOR`.
`actions delete <action-id>`	Remove Action.
`actions headers list <action-id>`	Print HTTP headers.
`actions headers add <action-id>`	Add header.
`actions headers remove <action-id>`	Remove header.

`actions create`

nora actions create \
  --name notify_slack \
  --description "Post a Slack message with the Agent's summary" \
  --runtime '{"kind":"http","method":"POST","url":"https://hooks.slack.com/services/xxx"}'

Flags:

--name <n> (required).
--description <d>.
--runtime <json> — HTTP or inline runtime spec (same shape as Tools).
--x <n>, --y <n> — canvas position.

`actions update`

nora actions update ac_notify \
  --set-approval on \
  --set-http-url https://hooks.slack.com/services/new-url

Update flags

Identity

--set-name <n>
--set-description <d>
--set-icon <name>

Approval

--set-approval on|off — require approval before firing.

HTTP runtime

--set-runtime-kind http|inline
--set-http-method <m>
--set-http-url <url>
--set-http-auth-kind <k>
--set-http-auth-header <name>
--set-http-auth-value <v>

Inline runtime

--set-inline-lang <lang>
--set-inline-code <text> / --set-inline-code-file <path>

Position/size

--set-x <n>, --set-y <n>, --set-width <n>

Bulk

--patch <json>

`actions edit`

nora actions edit ac_notify

`actions delete`

nora actions delete ac_notify

Removes the Action; wires prune.

`actions headers`

Same shape as Tools:

nora actions headers list ac_notify
nora actions headers add ac_notify --name Authorization --value 'secrets://slack_bot_token'
nora actions headers remove ac_notify --name X-Old-Header

Secret values via secrets://<ref>. Interactive with --value ?. See Piping & secrets.

Tool vs. Action — quick refresher

	Tool	Action
Who decides when to call	Agent (via LLM)	Flow (via wiring)
Who picks arguments	Agent	Mapped from Agent output
Runs during reasoning	Yes	After
Can affect the Agent’s next step	Yes	No

Rule of thumb: if the Agent might need the result to reason further, it’s a Tool. If it’s fire-and-forget after the answer, it’s an Action.

Recipes

Add a Slack notification with an approval gate

AC=$(nora actions create \
  --name notify_slack \
  --description "Post a Slack summary" \
  --runtime '{"kind":"http","method":"POST","url":"'$SLACK_WEBHOOK'"}' \
  | jq -r '.id')

nora actions update $AC --set-approval on

Every Slack post now waits for approval.

Migrate a header rotation

new_token='secrets://slack_bot_token_v2'
for id in $(nora flows get support | jq -r '.blocks[] | select(.kind=="action").id'); do
  nora actions headers remove $id --name Authorization 2>/dev/null
  nora actions headers add $id --name Authorization --value "$new_token"
done

Setup

Flows

Blocks

Data & knowledge

Reliability

Workspace

Reference

nora actions

Commands

`actions create`

`actions update`

Update flags

`actions edit`

`actions delete`

`actions headers`

Tool vs. Action — quick refresher

Recipes

Add a Slack notification with an approval gate

Migrate a header rotation

​Commands

​actions create

​actions update

​Update flags

​actions edit

​actions delete

​actions headers

​Tool vs. Action — quick refresher

​Recipes

​Add a Slack notification with an approval gate

​Migrate a header rotation

Commands

`actions create`

`actions update`

Update flags

`actions edit`

`actions delete`

`actions headers`

Tool vs. Action — quick refresher

Recipes

Add a Slack notification with an approval gate

Migrate a header rotation