Skip to content

[Bug]: Cursor provider: /skill and $skill can't invoke skills with disable-model-invocation: true (agent SDK) #15606

Open
Open
[Bug]: Cursor provider: /skill and $skill can't invoke skills with disable-model-invocation: true (agent SDK)#15606
Labels
bugSomething is broken or behaving incorrectly.via-triageFiled through npx t3 triage

Description

@cvpcasada
cvpcasada
opened on Oct 4, 2026

Before submitting

  • I searched existing issues and did not find a duplicate.
  • I included enough detail to reproduce or investigate the problem.

Area

apps/server

Steps to reproduce

  1. Put a skill in ~/.agents/skills/ whose frontmatter sets disable-model-invocation: true (for example grill-me).
  2. Open a Cursor thread in T3 Code.
  3. Send /grill-me <request> or $grill-me <request>.

Expected behavior

The skill's SKILL.md is loaded into the turn and the agent follows it, the same as typing /grill-me in Cursor's own composer.

Actual behavior

The agent receives /grill-me as plain text and can't find the skill.

The skill isn't missing from discovery. The model-facing skill list shows other skills from the same ~/.agents/skills/ folder (for example grilling and code-review). All 10 skills there with disable-model-invocation: true are absent: grill-me, implement, to-spec, handoff, show-me, retro, ask-matt, improve-codebase-architecture, grill-with-docs and setup-matt-pocock-skills.

For skills with disable-model-invocation: true, Cursor hides them from the model and only loads them when its own composer handles the slash command. The agent SDK has no equivalent expansion: the prompt reaches the model as text, and the skill was never listed, so the model has no way to look it up. The Claude fix (#7673 / #9161) hands /name to the CLI to expand. Cursor's SDK has nothing to hand it to, so T3 would need to expand it itself. On send, it would resolve a leading /name or $name against the discovered Cursor skills, including user-invocation-only ones, and add that skill's SKILL.md to the prompt.

Related: #6581 (Cursor skill picker and invocation), #9161 and #8295 (the same problem on the Claude provider), #13457 (the same problem on the Grok provider).

Impact

Major degradation or frequent failure

Version or commit

0.0.46-nightly.20261004.2648

Environment

macOS 27.0.1 (arm64), T3 Code desktop nightly, Cursor provider via the Cursor agent SDK with orchestrator v2

Workaround

Reference the file directly in the prompt (follow ~/.agents/skills/grill-me/SKILL.md), or remove disable-model-invocation from the skill.

Activity

  1. juliusmarminge commented on Oct 4, 2026

    @juliusmarminge
    juliusmarminge
    on Oct 4, 2026
    Member

    Note

    Grok responding on behalf of Julius.

    Triage

    Thanks for the detailed report, @cvpcasada. The frontmatter example and the side-by-side with grilling made this easy to trace.

    What I found

    I reproduced this from the code on current main. A Cursor skill with disable-model-invocation: true gets discovered and offered in the composer, but it's sent as plain prompt text, so the Agent SDK never attaches its SKILL.md.

    • parseSkillFrontmatter in CursorSkills.ts records the flag as userInvocationOnly and still returns the skill. The composer keeps it because isProviderSkillUserInvocable only filters out userInvocable: false.
    • On send, CursorAdapterV2.resolveUserMessage uses that same skill set, and rewriteCursorSkillMentions turns $grill-me into /grill-me. A typed /grill-me isn't a $ mention, so it's passed through unchanged. Either way, agent.send only receives a string. Its options are model, mode, MCP servers, and callbacks, with no skill field.
    • Cursor's docs say a disable-model-invocation skill is only included when Agent chat invokes /skill-name itself. The model-facing catalog comes from settingSources, which is why grilling shows up there and grill-me doesn't. Rewriting the token doesn't do the composer's attach step, so the model has neither a catalog entry nor the skill body.

    Related history: this isn't #6581, which was the empty Cursor skill picker (filesystem discovery has since landed). It's the same gap as #9161 and #8295 on Claude and the open #13457 on Grok, except Cursor already does the $ to / rewrite and that isn't enough here. #8336 tried inlining the skill file and was closed in favor of #9128, so the harness itself runs the skill (with allowed-tools, forks, hooks, and model overrides). That suggests inlining SKILL.md into the prompt isn't the direction either.

    Workaround for now: point the prompt at the skill file directly, or remove disable-model-invocation so Cursor lists the skill for the model again.

    Likely fix area

    • CursorAdapterV2.resolveUserMessage and rewriteCursorSkillMentions, if the Cursor SDK exposes (or gains) a way to attach a user-invoked skill on send.
    • CursorSkills.ts and isProviderSkillUserInvocable, if the better option is to hide or mark user-invocation-only skills in the Cursor composer until invocation is supported.

    A maintainer will decide on the fix direction.

  2. juliusmarminge
    added
    bugSomething is broken or behaving incorrectly.
    via-triageFiled through npx t3 triage
    on Oct 4, 2026

  3. Melv1C commented on Oct 8, 2026

    @Melv1C
    Melv1C
    on Oct 8, 2026

    I can reproduce this with the bro skill (~/.agents/skills/bro, disable-model-invocation: true).

    The composer lists it and the turn is sent as /bro. In a Cursor thread the model says no such skill exists. The same /bro prompt works in the agent CLI. The skill is installed, and the CLI loads it. The Agent SDK session T3 opens does not.

    Image

    This is painful for using Cursor inside T3. It sits next to #16430: the picker and the running agent still disagree about which Cursor skills are actually available.

    Is there a timeline for tackling this?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething is broken or behaving incorrectly.via-triageFiled through npx t3 triage

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions