Update to Synthflow
Snapshot Nov 9, 2026 · 18:08 UTC · version 1.1.0-6b3927081bed
Declared capabilities changed
Declared skills — Now says: [{"description":"Create, update, test, and attach Synthflow agent actions over MCP — custom HTTP actions, information extractors, transfers, SMS, real-time...
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Declared skills
Oct 27, 2026 · 00:34 UTC
[{"description":"Review the last 100 calls for an agent and surface problems. Use this whenever the user wants a call-quality audit, a QA pass over recent calls, a \"what's going wrong with this agent\" review, or to find failed, unresol...
Nov 9, 2026 · 18:08 UTC
[{"description":"Create, update, test, and attach Synthflow agent actions over MCP — custom HTTP actions, information extractors, transfers, SMS, real-time booking (Cal.com, GoHighLevel), IVR navigation, custom evaluations, and call-summ...
Composer icon dark url
Oct 27, 2026 · 00:34 UTC
https://files.openai.com/content?id=file_00000000d4ec81f4be80654a6d1dd188
Nov 9, 2026 · 18:08 UTC
Not present
Composer icon url
Oct 27, 2026 · 00:34 UTC
https://files.openai.com/content?id=file_00000000d4ec81f4be80654a6d1dd188
Nov 9, 2026 · 18:08 UTC
https://files.openai.com/content?id=file_00000000ff6481f48fd8c65f8568dd24
Logo url
Oct 27, 2026 · 00:34 UTC
https://files.openai.com/content?id=file_00000000991c824387e82a81fe82a544
Nov 9, 2026 · 18:08 UTC
https://files.openai.com/content?id=file_00000000dc7081f49dcdcbf7a3fb822c
Compare saved observations
Download comparison JSONFull technical diff · 7 changed fields
changed /release/id
"pluginrel_fc990d6d39e48191a91123e56ec602da"
"pluginrel_1e82abee39048191a96f63720ea3a879"
changed /release/interface/composer_icon_dark_url
"https://files.openai.com/content?id=file_00000000d4ec81f4be80654a6d1dd188"
null
changed /release/interface/composer_icon_url
"https://files.openai.com/content?id=file_00000000d4ec81f4be80654a6d1dd188"
"https://files.openai.com/content?id=file_00000000ff6481f48fd8c65f8568dd24"
changed /release/interface/logo_url
"https://files.openai.com/content?id=file_00000000991c824387e82a81fe82a544"
"https://files.openai.com/content?id=file_00000000dc7081f49dcdcbf7a3fb822c"
changed /release/interface/logo_url_dark
"https://files.openai.com/content?id=file_00000000991c824387e82a81fe82a544"
null
changed /release/skills
[
{
"description": "Review the last 100 calls for an agent and surface problems. Use this whenever the user wants a call-quality audit, a QA pass over recent calls, a \"what's going wrong with this agent\" review, or to find failed, unresolved, dropped, or otherwise problematic calls. Trigger on phrases like \"review my calls\", \"what's wrong with the calls\", \"QA the last 100 calls\", \"find bad calls\", or \"audit recent calls\".",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "call-review",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "radar",
"short_description": "Review the last 100 calls for an agent and surface problems. Use this whenever the user wants a call-quality audit, a QA pass over recent calls, a \"what's going wrong with this agent\" review, or to find failed, unresolved, dropped, or otherwise problematic calls. Trigger on phrases like \"review my calls\", \"what's wrong with the calls\", \"QA the last 100 calls\", \"find bad calls\", or \"audit recent calls\"."
},
"name": "call-review",
"plugin_release_skill_id": "pluginrsk_6a8d65d95ac481919417ae9c6265679e"
},
{
"description": "Review an AI agent prompt before it is tested, deployed, or edited in production. Use this when the user asks to review, audit, validate, improve, or build a new prompt.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "prompt-review",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "radar",
"short_description": "Review an AI agent prompt before it is tested, deployed, or edited in production. Use this when the user asks to review, audit, validate, improve, or build a new prompt."
},
"name": "prompt-review",
"plugin_release_skill_id": "pluginrsk_6a8d65e1ebc08191a2e6ee6cb54f5dc7"
}
][
{
"description": "Create, update, test, and attach Synthflow agent actions over MCP — custom HTTP actions, information extractors, transfers, SMS, real-time booking (Cal.com, GoHighLevel), IVR navigation, custom evaluations, and call-summary emails. Use this whenever the user wants to give an agent a new capability, connect it to an API or CRM, extract data from calls, add a transfer or SMS, set up booking, change an action's URL, body, or variables, or fix an action that isn't firing or is failing. Trigger on phrases like \"add an action\", \"call my API during the call\", \"extract the caller's email\", \"set up a transfer\", \"connect booking\", \"update the webhook URL\", or \"the action isn't working\".",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "build-action",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "bolt",
"short_description": "Create, update, test, and attach Synthflow agent actions over MCP — custom HTTP actions, information extractors, transfers, SMS, real-time booking (Cal.com, GoHighLevel), IVR navigation, custom evaluations, and call-summary emails. Use this whenever the user wants to give an agent a new capability, connect it to an API or CRM, extract data from calls, add a transfer or SMS, set up booking, change an action's URL, body, or variables, or fix an action that isn't firing or is failing. Trigger on phrases like \"add an action\", \"call my API during the call\", \"extract the caller's email\", \"set up a transfer\", \"connect booking\", \"update the webhook URL\", or \"the action isn't working\"."
},
"name": "build-action",
"plugin_release_skill_id": "pluginrsk_6af1ae96ac04819189f20118afab8306"
},
{
"description": "Build a call-volume and outcome report for a Synthflow agent, workspace, or agency — counts, durations, statuses, end-call reasons, call reasons from information extractors, transfer and booking results, and trends over a period. Use this whenever the user wants a daily, weekly, or monthly report, a call-reason breakdown, KPIs for a customer, an operations dashboard dataset, or numbers like \"how many calls did we get\", \"what are people calling about\", or \"what share of calls were transferred\". For a quality audit of individual calls, use the call-review skill instead.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "call-report",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "chart",
"short_description": "Build a call-volume and outcome report for a Synthflow agent, workspace, or agency — counts, durations, statuses, end-call reasons, call reasons from information extractors, transfer and booking results, and trends over a period. Use this whenever the user wants a daily, weekly, or monthly report, a call-reason breakdown, KPIs for a customer, an operations dashboard dataset, or numbers like \"how many calls did we get\", \"what are people calling about\", or \"what share of calls were transferred\". For a quality audit of individual calls, use the call-review skill instead."
},
"name": "call-report",
"plugin_release_skill_id": "pluginrsk_6af1ae967dd08191acfc0f97189c4ad2"
},
{
"description": "Review the last 100 calls for an agent and surface problems. Use this whenever the user wants a call-quality audit, a QA pass over recent calls, a \"what's going wrong with this agent\" review, or to find failed, unresolved, dropped, or otherwise problematic calls. Trigger on phrases like \"review my calls\", \"what's wrong with the calls\", \"QA the last 100 calls\", \"find bad calls\", or \"audit recent calls\".",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "call-review",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "radar",
"short_description": "Review the last 100 calls for an agent and surface problems. Use this whenever the user wants a call-quality audit, a QA pass over recent calls, a \"what's going wrong with this agent\" review, or to find failed, unresolved, dropped, or otherwise problematic calls. Trigger on phrases like \"review my calls\", \"what's wrong with the calls\", \"QA the last 100 calls\", \"find bad calls\", or \"audit recent calls\"."
},
"name": "call-review",
"plugin_release_skill_id": "pluginrsk_6af1ae96f7c48191af60b9d1e5d5fc37"
},
{
"description": "Investigate why a specific Synthflow call (or a small set of similar calls) went wrong — failed or missed transfers, calls cut off, the agent going silent or repeating itself, actions or webhooks that didn't fire or failed, wrong data captured, or outbound calls that didn't connect. Use this whenever the user points at a call or a phone number and asks what happened or why, e.g. \"why did this call drop\", \"the transfer didn't ring\", \"the booking didn't happen on this call\", \"the webhook never arrived\", or \"check the call from +1… this morning\". For an audit of many recent calls, use the call-review skill instead.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "diagnose-call",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "radar",
"short_description": "Investigate why a specific Synthflow call (or a small set of similar calls) went wrong — failed or missed transfers, calls cut off, the agent going silent or repeating itself, actions or webhooks that didn't fire or failed, wrong data captured, or outbound calls that didn't connect. Use this whenever the user points at a call or a phone number and asks what happened or why, e.g. \"why did this call drop\", \"the transfer didn't ring\", \"the booking didn't happen on this call\", \"the webhook never arrived\", or \"check the call from +1… this morning\". For an audit of many recent calls, use the call-review skill instead."
},
"name": "diagnose-call",
"plugin_release_skill_id": "pluginrsk_6af1ae95ad9481918cc3868b68bf221d"
},
{
"description": "Review AI voice-agent prompts, especially Synthflow Single-Prompt, for contradictions, missing context, unsafe tool/action behavior, escalation gaps, compliance risk, and regression risk. Use this when the user asks to review, audit, validate, improve, or compare a prompt before deployment.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "prompt-review",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Review AI voice-agent prompts, especially Synthflow Single-Prompt, for contradictions, missing context, unsafe tool/action behavior, escalation gaps, compliance risk, and regression risk. Use this when the user asks to review, audit, validate, improve, or compare a prompt before deployment."
},
"name": "prompt-review",
"plugin_release_skill_id": "pluginrsk_6af1ae96cec081919299ecfb5a8ef4a0"
},
{
"description": "Build and run simulated-caller tests against a Synthflow voice agent, then report which scenarios pass or fail with transcript evidence. Use this whenever the user wants to test an agent before or after a change, check that a prompt fix works, reproduce a failure from a real call, build a test suite, or re-run existing simulations. Trigger on phrases like \"test the agent\", \"run the simulations\", \"regression test\", \"make sure this didn't break anything\", \"build a test suite\", \"reproduce this call\", or \"re-run the tests\".",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "regression-test",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Build and run simulated-caller tests against a Synthflow voice agent, then report which scenarios pass or fail with transcript evidence. Use this whenever the user wants to test an agent before or after a change, check that a prompt fix works, reproduce a failure from a real call, build a test suite, or re-run existing simulations. Trigger on phrases like \"test the agent\", \"run the simulations\", \"regression test\", \"make sure this didn't break anything\", \"build a test suite\", \"reproduce this call\", or \"re-run the tests\"."
},
"name": "regression-test",
"plugin_release_skill_id": "pluginrsk_6af1ae95af148191b5ed5a754d3cca1b"
},
{
"description": "Make a change to a live Synthflow voice agent safely — record a baseline, save a draft, review the diff, publish only on approval, verify the published state, and roll back if needed. Use this whenever the user wants to edit, update, fix, tweak, or publish an agent's prompt, greeting, voice, transcriber, LLM, actions, or any other setting, or wants to roll an agent back. Trigger on phrases like \"update the prompt\", \"change the voice\", \"fix the agent\", \"publish the draft\", \"push this live\", \"roll back the agent\", or \"undo the last change\".",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "safe-agent-change",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "bolt",
"short_description": "Make a change to a live Synthflow voice agent safely — record a baseline, save a draft, review the diff, publish only on approval, verify the published state, and roll back if needed. Use this whenever the user wants to edit, update, fix, tweak, or publish an agent's prompt, greeting, voice, transcriber, LLM, actions, or any other setting, or wants to roll an agent back. Trigger on phrases like \"update the prompt\", \"change the voice\", \"fix the agent\", \"publish the draft\", \"push this live\", \"roll back the agent\", or \"undo the last change\"."
},
"name": "safe-agent-change",
"plugin_release_skill_id": "pluginrsk_6af1ae95d27c8191ac7eff91477c12e4"
}
]changed /release/version
"1.0.0-6b3927081bed"
"1.1.0-6b3927081bed"
Full snapshot data
{
"canonical_app_id": "templated_apps_6a8d61e3eb088191a6116aa249be72cd",
"connector_id": null,
"created_at": "2026-08-25T09:35:32.167025Z",
"discoverability": "LISTED",
"id": "plugin_templated_apps_6a8d61e3eb088191a6116aa249be72cd",
"is_template": true,
"is_template_instance": false,
"is_v2_template": false,
"name": "app-6a8d61e3eb088191a6116aa249be72cd",
"release": {
"app_ids": [],
"app_manifest": null,
"app_templates": [
{
"can_setup": false,
"canonical_connector_id": null,
"description": "Synthflow lets you build and operate AI voice agents that make and take phone calls. This connector brings your Synthflow workspace into ChatGPT, so you can create and configure voice agents; manage their actions (SMS, call transfers, bookings, custom API calls, and data extraction); organize knowledge bases, phone numbers, and contacts; review calls and analytics; and run agent simulations — all from chat. It reads your workspace data and can make changes on your behalf; destructive actions like deletions are clearly marked.",
"instances": [],
"logo_url": "",
"logo_url_dark": "",
"materialized_app_ids": [],
"name": "Synthflow",
"reason": "NO_ACTIVE_WORKSPACE",
"template_id": "templated_apps_6a8d61e3eb088191a6116aa249be72cd"
}
],
"description": "Synthflow lets you build and operate AI voice agents that make and take phone calls. This connector brings your Synthflow workspace into ChatGPT, so you can create and configure voice agents; manage their actions (SMS, call transfers, bookings, custom API calls, and data extraction); organize knowledge bases, phone numbers, and contacts; review calls and analytics; and run agent simulations — all from chat. It reads your workspace data and can make changes on your behalf; destructive actions like deletions are clearly marked.",
"display_name": "Synthflow",
"id": "pluginrel_1e82abee39048191a96f63720ea3a879",
"interface": {
"brand_color": null,
"capabilities": [],
"category": "Productivity",
"composer_icon_dark_url": null,
"composer_icon_url": "https://files.openai.com/content?id=file_00000000ff6481f48fd8c65f8568dd24",
"default_prompt": "How did my voice agents perform over the last 7 days? Summarize call volume, completion rates, and any trends.",
"default_prompts": [
"How did my voice agents perform over the last 7 days? Summarize call volume, completion rates, and any trends.",
"Create a new inbound voice agent called \"Reception\" that greets callers and takes messages.",
"Simulate a frustrated caller rescheduling an appointment against my agent and tell me what to improve."
],
"developer_name": "Synthflow",
"logo_url": "https://files.openai.com/content?id=file_00000000dc7081f49dcdcbf7a3fb822c",
"logo_url_dark": null,
"long_description": "Synthflow lets you build and operate AI voice agents that make and take phone calls. This connector brings your Synthflow workspace into ChatGPT, so you can create and configure voice agents; manage their actions (SMS, call transfers, bookings, custom API calls, and data extraction); organize knowledge bases, phone numbers, and contacts; review calls and analytics; and run agent simulations — all from chat. It reads your workspace data and can make changes on your behalf; destructive actions like deletions are clearly marked.",
"plugin_category_id": "productivity",
"privacy_policy_url": "https://docs.synthflow.ai/privacy-policy",
"screenshot_urls": [],
"short_description": "Manage AI voice agents",
"terms_of_service_url": "https://docs.synthflow.ai/terms-conditions",
"website_url": "https://synthflow.ai/"
},
"keywords": [],
"mcp_servers": [],
"onboarding_skill_name": null,
"requires_local_executor": false,
"skills": [
{
"description": "Create, update, test, and attach Synthflow agent actions over MCP — custom HTTP actions, information extractors, transfers, SMS, real-time booking (Cal.com, GoHighLevel), IVR navigation, custom evaluations, and call-summary emails. Use this whenever the user wants to give an agent a new capability, connect it to an API or CRM, extract data from calls, add a transfer or SMS, set up booking, change an action's URL, body, or variables, or fix an action that isn't firing or is failing. Trigger on phrases like \"add an action\", \"call my API during the call\", \"extract the caller's email\", \"set up a transfer\", \"connect booking\", \"update the webhook URL\", or \"the action isn't working\".",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "build-action",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "bolt",
"short_description": "Create, update, test, and attach Synthflow agent actions over MCP — custom HTTP actions, information extractors, transfers, SMS, real-time booking (Cal.com, GoHighLevel), IVR navigation, custom evaluations, and call-summary emails. Use this whenever the user wants to give an agent a new capability, connect it to an API or CRM, extract data from calls, add a transfer or SMS, set up booking, change an action's URL, body, or variables, or fix an action that isn't firing or is failing. Trigger on phrases like \"add an action\", \"call my API during the call\", \"extract the caller's email\", \"set up a transfer\", \"connect booking\", \"update the webhook URL\", or \"the action isn't working\"."
},
"name": "build-action",
"plugin_release_skill_id": "pluginrsk_6af1ae96ac04819189f20118afab8306"
},
{
"description": "Build a call-volume and outcome report for a Synthflow agent, workspace, or agency — counts, durations, statuses, end-call reasons, call reasons from information extractors, transfer and booking results, and trends over a period. Use this whenever the user wants a daily, weekly, or monthly report, a call-reason breakdown, KPIs for a customer, an operations dashboard dataset, or numbers like \"how many calls did we get\", \"what are people calling about\", or \"what share of calls were transferred\". For a quality audit of individual calls, use the call-review skill instead.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "call-report",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "chart",
"short_description": "Build a call-volume and outcome report for a Synthflow agent, workspace, or agency — counts, durations, statuses, end-call reasons, call reasons from information extractors, transfer and booking results, and trends over a period. Use this whenever the user wants a daily, weekly, or monthly report, a call-reason breakdown, KPIs for a customer, an operations dashboard dataset, or numbers like \"how many calls did we get\", \"what are people calling about\", or \"what share of calls were transferred\". For a quality audit of individual calls, use the call-review skill instead."
},
"name": "call-report",
"plugin_release_skill_id": "pluginrsk_6af1ae967dd08191acfc0f97189c4ad2"
},
{
"description": "Review the last 100 calls for an agent and surface problems. Use this whenever the user wants a call-quality audit, a QA pass over recent calls, a \"what's going wrong with this agent\" review, or to find failed, unresolved, dropped, or otherwise problematic calls. Trigger on phrases like \"review my calls\", \"what's wrong with the calls\", \"QA the last 100 calls\", \"find bad calls\", or \"audit recent calls\".",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "call-review",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "radar",
"short_description": "Review the last 100 calls for an agent and surface problems. Use this whenever the user wants a call-quality audit, a QA pass over recent calls, a \"what's going wrong with this agent\" review, or to find failed, unresolved, dropped, or otherwise problematic calls. Trigger on phrases like \"review my calls\", \"what's wrong with the calls\", \"QA the last 100 calls\", \"find bad calls\", or \"audit recent calls\"."
},
"name": "call-review",
"plugin_release_skill_id": "pluginrsk_6af1ae96f7c48191af60b9d1e5d5fc37"
},
{
"description": "Investigate why a specific Synthflow call (or a small set of similar calls) went wrong — failed or missed transfers, calls cut off, the agent going silent or repeating itself, actions or webhooks that didn't fire or failed, wrong data captured, or outbound calls that didn't connect. Use this whenever the user points at a call or a phone number and asks what happened or why, e.g. \"why did this call drop\", \"the transfer didn't ring\", \"the booking didn't happen on this call\", \"the webhook never arrived\", or \"check the call from +1… this morning\". For an audit of many recent calls, use the call-review skill instead.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "diagnose-call",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "radar",
"short_description": "Investigate why a specific Synthflow call (or a small set of similar calls) went wrong — failed or missed transfers, calls cut off, the agent going silent or repeating itself, actions or webhooks that didn't fire or failed, wrong data captured, or outbound calls that didn't connect. Use this whenever the user points at a call or a phone number and asks what happened or why, e.g. \"why did this call drop\", \"the transfer didn't ring\", \"the booking didn't happen on this call\", \"the webhook never arrived\", or \"check the call from +1… this morning\". For an audit of many recent calls, use the call-review skill instead."
},
"name": "diagnose-call",
"plugin_release_skill_id": "pluginrsk_6af1ae95ad9481918cc3868b68bf221d"
},
{
"description": "Review AI voice-agent prompts, especially Synthflow Single-Prompt, for contradictions, missing context, unsafe tool/action behavior, escalation gaps, compliance risk, and regression risk. Use this when the user asks to review, audit, validate, improve, or compare a prompt before deployment.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "prompt-review",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Review AI voice-agent prompts, especially Synthflow Single-Prompt, for contradictions, missing context, unsafe tool/action behavior, escalation gaps, compliance risk, and regression risk. Use this when the user asks to review, audit, validate, improve, or compare a prompt before deployment."
},
"name": "prompt-review",
"plugin_release_skill_id": "pluginrsk_6af1ae96cec081919299ecfb5a8ef4a0"
},
{
"description": "Build and run simulated-caller tests against a Synthflow voice agent, then report which scenarios pass or fail with transcript evidence. Use this whenever the user wants to test an agent before or after a change, check that a prompt fix works, reproduce a failure from a real call, build a test suite, or re-run existing simulations. Trigger on phrases like \"test the agent\", \"run the simulations\", \"regression test\", \"make sure this didn't break anything\", \"build a test suite\", \"reproduce this call\", or \"re-run the tests\".",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "regression-test",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Build and run simulated-caller tests against a Synthflow voice agent, then report which scenarios pass or fail with transcript evidence. Use this whenever the user wants to test an agent before or after a change, check that a prompt fix works, reproduce a failure from a real call, build a test suite, or re-run existing simulations. Trigger on phrases like \"test the agent\", \"run the simulations\", \"regression test\", \"make sure this didn't break anything\", \"build a test suite\", \"reproduce this call\", or \"re-run the tests\"."
},
"name": "regression-test",
"plugin_release_skill_id": "pluginrsk_6af1ae95af148191b5ed5a754d3cca1b"
},
{
"description": "Make a change to a live Synthflow voice agent safely — record a baseline, save a draft, review the diff, publish only on approval, verify the published state, and roll back if needed. Use this whenever the user wants to edit, update, fix, tweak, or publish an agent's prompt, greeting, voice, transcriber, LLM, actions, or any other setting, or wants to roll an agent back. Trigger on phrases like \"update the prompt\", \"change the voice\", \"fix the agent\", \"publish the draft\", \"push this live\", \"roll back the agent\", or \"undo the last change\".",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "safe-agent-change",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "bolt",
"short_description": "Make a change to a live Synthflow voice agent safely — record a baseline, save a draft, review the diff, publish only on approval, verify the published state, and roll back if needed. Use this whenever the user wants to edit, update, fix, tweak, or publish an agent's prompt, greeting, voice, transcriber, LLM, actions, or any other setting, or wants to roll an agent back. Trigger on phrases like \"update the prompt\", \"change the voice\", \"fix the agent\", \"publish the draft\", \"push this live\", \"roll back the agent\", or \"undo the last change\"."
},
"name": "safe-agent-change",
"plugin_release_skill_id": "pluginrsk_6af1ae95d27c8191ac7eff91477c12e4"
}
],
"version": "1.1.0-6b3927081bed"
},
"scope": "GLOBAL",
"share_url": "https://chatgpt.com/plugins/plugin_templated_apps_6a8d61e3eb088191a6116aa249be72cd?open_in_app",
"status": "DISABLED_BY_ADMIN"
}SHA-256 of public snapshot: acc67ee8b043c6d1b5c81b52f06138b4b66b34cb5db24736cecb101f45ba73b4