commit 5a4ce934d63d1ca5cd106e5d32c8121f95fd8f39
parent b90433eebab525c743255b017e62c93319688a9a
Author: andrewlaack-collab <andrew.laack@imbue.com>
Date: Wed, 25 Feb 2026 22:23:01 -0600
Updated skill messaging (#153)
* Updated skill messaging
* Word
* Words
* More explicit
* Updated
---------
Co-authored-by: Andrew Laack <andrew@laack.co>
Diffstat:
1 file changed, 16 insertions(+), 4 deletions(-)
diff --git a/skills/vet/SKILL.md b/skills/vet/SKILL.md
@@ -59,6 +59,8 @@ vet "goal"
### Finding Your Session
+You should only search for sessions from your coding harness. If a user requests you use a different harness, they are likely referring to vet's agentic mode, not the session.
+
**OpenCode:** The `--session-id` argument requires a `ses_...` session ID. To find the current session ID:
1. Run: `opencode session list --format json` to list recent sessions with their IDs and titles.
2. Identify the current session from the list by matching the title or timestamp.
@@ -86,15 +88,25 @@ Vet analyzes the full git diff from the base commit. This may include changes fr
## Common Options
- `--base-commit REF`: Git ref for diff base (default: HEAD)
-- `--model MODEL`: LLM model to use (default: claude-opus-4-6)
+- `--model MODEL`: LLM to use (default: claude-opus-4-6)
+- `--list-models`: list all models that are supported by vet
+ - Run `vet --help` and look at the vet repo's readme for details about defining custom OpenAI-compatible models.
- `--confidence-threshold N`: Minimum confidence 0.0-1.0 (default: 0.8)
- `--output-format FORMAT`: Output as `text`, `json`, or `github`
- `--quiet`: Suppress status messages and 'No issues found.'
-- `--agentic`: Mode that routes analysis through the locally installed Claude Code or Codex CLI instead of calling the API directly. Try this if vet fails due to missing API keys. Slower (~3 min) so not recommended as the default.
+- `--agentic`: Mode that routes analysis through the locally installed Claude Code or Codex CLI instead of calling the API directly. Try this if vet fails due to missing API keys. This is slower (~3 min) so it is not the default, but it often results in higher precision issue identification.
+- `--agent-harness`: The two options for this are `codex` and `claude`. Claude Code is the default.
- `--help`: Show comprehensive list of options
+
## Updating
-The vet CLI, skill files, and export scripts can become outdated as things change. The export scripts in particular are tightly coupled to the session storage formats of Codex, Claude Code, and OpenCode, which will change over time.
+The vet CLI, skill files, and export scripts can become outdated as agent harnesses and LLM APIs change.
+
+If this happens, try updating them. Run `which vet` to determine how vet was installed and update accordingly. For the skill files, check which skill directories exist on disk and update them with the latest versions from https://github.com/imbue-ai/vet/tree/main/skills/vet.
+
+## Additional Information
+
+Additional information can be found in the vet repo:
-If vet or the export scripts fail unexpectedly, try updating them. Run `which vet` to determine how vet was installed and update accordingly. For the skill files, check which skill directories exist on disk and update them with the latest versions from https://github.com/imbue-ai/vet/tree/main/skills/vet.
+https://github.com/imbue-ai/vet
