/validator-commit $ARGUMENTS
SkillAI & modelsActivates only for explicit validator-aware commit requests such as "commit with validator", "run validator then commit", "run checks before commit", or "skip validator and commit". Excludes plain commit requests.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the /validator-commit $ARGUMENTS skill
What this skill tells your AI
The instructions your AI receives, as published by codagent-ai/agent-validator in skills/validator-commit/SKILL.md and read by ahel’s review.
Commit with explicit validator validation intent. Runs agent-validate detect first, validates based on intent (full run, checks only, or skip), handles failures, then commits.
Invocation Policy
Use this skill only when the user explicitly asks to involve Agent Validator in the commit flow, including full validation, checks-only validation, or intentionally skipping validator state as part of the commit.
Do not choose this skill for a plain "commit", "make a commit", or "commit these changes" request that does not mention validator, gauntlet, checks, validation, or skip.
Step 1 - Detect Changes
Run agent-validate detect using Bash:
agent-validate detect 2>&1; echo "DETECT_EXIT:$?"
Check the exit code from the DETECT_EXIT: line:
- Exit 0 → gates would run, continue to Step 2
- Exit 2 → no gates would run (no changes or no applicable gates), skip to Step 4 (commit directly)
- Exit 1 → error, report the error to the user and stop
- Any other exit code → treat as error, report output to the user, and stop
Step 2 - Determine Validation Intent
Parse $ARGUMENTS for a validation intent. Do not prompt the user if a clear intent is found.
| ARGUMENTS pattern | Action |
|---|---|
| Contains "check" or "checks" | Invoke /validator-check (Step 3b) |
| Contains "run", "full", or "all gates" | Invoke /validator-run (Step 3a) |
| Contains "skip" | Run agent-validate skip 2>&1 (Step 3c), then go to Step 4 |
| Empty or no clear intent | Present the three choices below to the user, wait for selection |
Evaluate the "check" or "checks" pattern before the generic "run" pattern, so
phrases like "run checks before commit" select /validator-check.
When prompting the user, present these choices:
- Run all gates — full validation (checks + reviews)
- Run checks only — checks without AI reviews
- Skip validator — advance baseline without running any gates
Then proceed to the step matching the user's selection.
Step 3a - Full Validation (validator-run)
Invoke /validator-run.
- If it passes → go to Step 4
- If it fails → the
/validator-runskill handles fixing and re-running. After that skill completes, ask the user: "Ready to commit?". Proceed to Step 4 only on confirmation.
Step 3b - Checks-Only Validation (validator-check)
Invoke /validator-check.
- If it passes → go to Step 4
- If it fails → the
/validator-checkskill handles fixing and re-running. After that skill completes, ask the user: "Ready to commit?". Proceed to Step 4 only on confirmation.
Step 3c - Skip Validation
Run:
agent-validate skip 2>&1
Report the command output to the user, then go to Step 4.
Step 4 - Commit
Check whether you have a skill for committing git changes available (excluding validator-commit itself to avoid self-invocation).
- If a commit skill is found → invoke that skill to perform the commit
- If no commit skill is found → stage all tracked changes, propose a commit message following the conventional commits format (
<type>: <description>), then rungit commit -m "<message>"
Signals
- GitHub stars
- 29
- Forks
- 2
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
validator-commit- Source
- github.com/codagent-ai/agent-validator