disable-model-invocation hides commands from skill list, blocking user-initiated invocation

[myleshungerford]

Problem

Commands with disable-model-invocation: true in their frontmatter (e.g., review.md, adversarial-review.md, cancel.md, result.md, status.md) are completely hidden from the skill list presented to Claude at conversation start. This means Claude has no awareness these commands exist.

When a user explicitly types /codex:review in conversation, Claude cannot route to it because it's not in the visible skill list. In practice, Claude either:

1. Silently reroutes to a different command (e.g., codex:rescue) that IS visible, or
2. Tells the user the command doesn't exist

Both outcomes are wrong. The user asked for a specific command by name and didn't get it.

Root Cause

disable-model-invocation: true conflates two separate concerns:

1. Preventing proactive model invocation (Claude shouldn't spontaneously decide to run a review)
2. Making the model aware a command exists (so it can route explicit user requests)

Currently one flag controls both. Commands with the flag set are invisible to the model entirely, even when the user explicitly requests them.

Affected Commands

Command	Has flag	In skill list
review	yes	no
adversarial-review	yes	no
cancel	yes	no
result	yes	no
status	yes	no
rescue	no	yes
setup	no	yes

Suggested Fix

Separate the two concerns. Options:

• Option A: Add commands with disable-model-invocation: true to the skill list but mark them as user-initiated only, so Claude knows they exist but won't proactively call them.
• Option B: Ensure the Skill tool resolver can match user-typed /codex:review to the command file even when the command isn't in the proactive skill list.
• Option C: Introduce a second frontmatter key (e.g., hidden: true vs disable-model-invocation: true) to distinguish "hide from model entirely" from "don't let model call proactively."

Environment

• codex-cli 0.117.0
• Plugin version 1.0.3
• Claude Code on Windows 11

[myleshungerford]

Additional finding: Skill tool also blocked

Confirmed that disable-model-invocation: true blocks the Skill tool entirely, not just the proactive skill list. When Claude attempts to invoke codex:review via the Skill tool (in response to an explicit user request in conversation), it returns:

Skill codex:review cannot be used with Skill tool due to disable-model-invocation

This means these commands are only reachable when the user types the slash command directly in the CLI prompt. There is no workaround available from within a conversation, even when the user explicitly asks Claude to run the command. Claude cannot comply.

This elevates the severity: a CLAUDE.md workaround listing the hidden commands is insufficient because even knowing they exist, Claude cannot invoke them.

[justmumu]

+1. This makes the plugin completely useless.

[ryantomlinson95]

+1, can't have the model trigger this as part of other skills or workflows really kills the usefulness

[flub71]

+1, this has broken recently - it was perfect when I tried it 2 days ago.