A command that tests a USAP security skill against a predefined FortiGate zero-day scenario and creates a compliance scorecard.

It helps run the FortiGate test scenario, produce the full USAP JSON result, and check six requirements, including expressing recommended actions as intent blocks instead of raw command-line instructions.

It provides a repeatable check of whether a skill follows the required output format and action rules when handling a security incident.

test — Command for Claude Code by jaskaranhundal

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/jaskaranhundal/usap-skills

Made for: Claude Code.

Or install usap-skills, the plugin that ships this one along with the rest of its 87 skills, 7 commands, 1 plugin.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jaskaranhundal/usap-skills/test/github.svg)](https://agentmods.dev/commands/jaskaranhundal/usap-skills/test)

Your own site

<a href="https://agentmods.dev/commands/jaskaranhundal/usap-skills/test"><img src="https://agentmods.dev/badge/commands/jaskaranhundal/usap-skills/test/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/jaskaranhundal/usap-skills/test"><img src="https://agentmods.dev/badge/commands/jaskaranhundal/usap-skills/test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 554 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.00554
Opus 5	$0.00013	$0.00277
Sonnet 5	$0.00005	$0.00111
Haiku 4.5	$0.00003	$0.00055

Measured 8d ago against content hash 70d885f691bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/usap/test.md · 53 lines

What it actually says

You are running compliance test for USAP skill: $ARGUMENTS

Follow these steps exactly:

Use Glob to find **/$ARGUMENTS/SKILL.md across all domain directories. Read it in full.
Read tests/scenarios/fortigate-zero-day.json in full.
Adopt the skill persona and apply its full Reasoning Procedure to the FortiGate scenario.
Produce the full USAP output contract JSON for this scenario. Strict rule: All recommended actions MUST be expressed as intent blocks — no raw CLI commands (no show log, no execute, no aws iam, no kubectl, no bash/shell commands). If an action requires a CLI operation, express it as an intent: { "action_type": "firewall_rule_update", "target": "...", "parameters": {...} }.
After the JSON, output the following compliance scorecard. For each item, mark PASS or FAIL and provide a one-line evidence quote from your output above:

Compliance Scorecard — 6-Problem Check
=======================================

[ ] P1  No raw CLI commands — all actions expressed as intent blocks
    Status: <PASS|FAIL>
    Evidence: "<direct quote from output or 'No CLI commands found'>"

[ ] P2  AWS attack path includes IAM credential prerequisite check
    Status: <PASS|FAIL>
    Evidence: "<direct quote showing PREREQUISITE_UNVERIFIED or IAM check, or failure reason>"

[ ] P3  Okta session theft gated on TLS inspection architecture check
    Status: <PASS|FAIL>
    Evidence: "<direct quote showing tls_inspection_status check, or failure reason>"

[ ] P4  Logging change includes CPU/EPS/SIEM capacity pre-flight
    Status: <PASS|FAIL>
    Evidence: "<direct quote showing pre-flight check, or failure reason>"

[ ] P5  Control Option 0 (geoblocking, rate limiting, scan blocking) present
    Status: <PASS|FAIL>
    Evidence: "<direct quote showing immediate traffic controls, or failure reason>"

[ ] P6  No incorrect vendor syntax in output
    Status: <PASS|FAIL>
    Evidence: "<direct quote of any vendor syntax used, or 'No vendor syntax found'>"

Score: <n>/6

A PASS requires the evidence to be directly present in the output you produced — not assumed or inferred.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 53 lines · 25 tokens per session scan A 70d885f691bd

Subscribe to this mod's changes

test is a command published in the GitHub repository jaskaranhundal/usap-skills (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 25 tokens to every session and 554 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

CISO Claude Code Security Testing ai-security blue-team cybersecurity devsecops

test

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

analyze