main.js · part 106

60 text occurrences from desktop/Cursor.app/Contents/Resources/app/extensions/cursor-local-agent-runtime/dist/main.js, part 106. Every entry preserves the shipped literal and its saved verdict or selection reason.

File contents and all parts · All files

${t}

... (git status truncated)

${vJ(e.content??"")}, glob pattern(s) for applicable files: ${t}

${vJ(e.content??"")}, applicable for all files within ${t}

at:
${s.map(e=>`- ${e.path}`).join("\n")}

- ${e.path}

at ${s[0].path}

Yes (potentially incomplete while git repository detection is still warming), currently found ${g}

Unknown (git repository detection still warming)

Yes, ${g}

OS Version: 

Workspace Paths:

Workspace Path: 

Workspace Path: unknown

Is directory a git repo: 

Terminals folder: 

Today's date: 

Agent shared notes folder: 

Meta-agent notes folder: ${u}

Agent conversation notes folder: ${c}

Note: Prefer using absolute paths over relative paths as tool call args when possible.

OS Version: 

Workspace Paths:

Workspace Path: 

Workspace Path: unknown

Is directory a git repo: 

Today's date: 

Terminals folder: 

Agent shared notes folder: 

Meta-agent notes folder: ${u}

Agent conversation notes folder: ${c}

This cloud workspace has multiple independent git repositories, each listed below with its own status.

${i} The agent process initial working directory is ${s}.

This is the git status at the start of the conversation. Note that this status is a snapshot in time, and will not update during the conversation.

Git repo: 

 (remote: ${r})

Agent transcripts (past chats) live in 

. They have names like

cite parent chat transcripts to the user as [<title for chat <=6 words>](<uuid excluding .jsonl>).

 Do not cite subagent transcript files from this folder.

Don't discuss the folder structure.

Don't cite the file directly to the user.

These are workspace-level rules that the agent must always follow.

These are workspace-level rules that the agent should follow. Use the ${t} tool to fetch full contents from the provided absolute path. Read each rule file using the ${t} tool when it is relevant to your work.

These are workspace-level rules that the agent should follow. Fetch full contents from the provided absolute path.

Skills the agent can use. Use the ${s} tool with the provided absolute path to fetch full contents.

Skills the agent can use. Fetch full contents from the provided absolute path.

When the user names a skill, use it faithfully as part of the current task.

 Read the skill file using the ${s} tool before following its instructions.

 Read the skill file before following its instructions.

The user's instructions take precedence over skill guidance, and an invoked skill takes precedence over autonomous judgment where they do not conflict.

Tell the user in `commentary` when a skill causes a material action or pause. Before using a skill the user did not name, briefly explain why it is relevant and keep its use within the task's scope. Mention material effects in the final response, but do not cite skills you merely inspected.

No skills are listed below, but additional skills may exist in the directories shown in the skills section if a later task specifically requires discovering more skills.

Use the skills listed below. If a later task specifically requires discovering more skills, additional skills may exist in the directories shown in the skills section.

Only use skills listed below.

When users ask you to perform tasks, check if any of the available skills below can help complete the task more effectively. Skills provide specialized capabilities and domain knowledge.

 To use a skill, read the skill file at the provided absolute path using the ${s} tool, then follow the instructions within.

 To use a skill, read the skill file at the provided absolute path, then follow the instructions within.

When a skill is relevant, read and follow it IMMEDIATELY as your first action. NEVER just announce or mention a skill without actually reading and following it.

No skills are listed below, but additional skills may exist in the directories shown in the skills section if a later task specifically requires discovering more skills.

Use the skills listed below. If a later task specifically requires discovering more skills, additional skills may exist in the directories shown in the skills section.