Diagnose, install, and verify Agent Guard's plugin-local binary, jq and gitleaks dependencies, the active host integration, and live hook protection.
SkillScore70Maintained
Automatic
◆Security & AppSec pack
Last verified 8/15/2026
What it changes
Passed 13 of 19 test cases with the skill, and 5 of 19 without it.
Without skill26%
With skill70%
Checks it passed that the model alone missed
Runs `check` followed by `smoke-test` on the resolved binary.
Directs the user to review and trust hooks through the Codex Settings UI.
Explains that local check commands do not prove active host hook dispatch.
and 12 more in the full report
10 fixed6 passed either way7 still failing0 broke
Pass-rate lift
+43 pp
Tokens
+43%
Agent turns
0%
Response time
-48%
Model gemini-3.6-flashMeasured 8/15/2026v116 of 23 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
What is the initial diagnostic command to run against the agent-guard executable, and should it attempt to automatically fix missing packages?
What was checked, without and with the skill
Checked
Without skill
With skill
Invokes `setup` on the resolved executable path as the initial diagnostic step.
Missed
Passed
Explains that `setup` without `--install` acts as a read-only inspection tool that does not modify the system.
Missed
Passed
case-06 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md89 linessingle file
Setup Agent Guard
Make Agent Guard operational without silently changing the machine. Diagnose first, request approval before package-manager or download actions, and finish with a real smoke test.
Workflow
Resolve the Agent Guard executable without confusing the plugin with a standalone install.
First use the plugin binary two directories above this skill: ../../bin/agent-guard relative to this SKILL.md directory.
Resolve the path from the skill directory, confirm that it is executable, and use it for every plugin diagnosis and smoke test.
Separately inspect command -v agent-guard, if present. Compare its version with the plugin binary and report version drift, but do not substitute it for the plugin binary or modify the standalone installation without explicit approval.
Only fall back to command -v agent-guard when the plugin-relative binary is unavailable, and clearly state that plugin-local verification could not be completed.
Do not install a second copy of Agent Guard merely to get a command on PATH.
Run the read-only diagnosis:
"<agent-guard-bin>" setup
If jq is missing, identify the available system package manager and show the exact install command. Ask for explicit user approval before running it. Do not use sudo unless the user explicitly approves elevated installation.
If gitleaks is missing, prefer Agent Guard's private, checksum-pinned installer:
Determine the target OS and architecture.
Fetch the official checksum list for the version reported by agent-guard setup.
Select the checksum for the exact archive name and show the version, archive, source URL, checksum, and destination.
Ask for explicit approval before downloading or installing.