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.
git clone --depth 1 https://github.com/jaskaranhundal/usap-skillsWrote 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.
[](https://agentmods.dev/commands/jaskaranhundal/usap-skills/fortigate)<a href="https://agentmods.dev/commands/jaskaranhundal/usap-skills/fortigate"><img src="https://agentmods.dev/badge/commands/jaskaranhundal/usap-skills/fortigate/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.
<a href="https://agentmods.dev/commands/jaskaranhundal/usap-skills/fortigate"><img src="https://agentmods.dev/badge/commands/jaskaranhundal/usap-skills/fortigate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00031 | $0.02115 |
| Opus 5 | $0.00015 | $0.01058 |
| Sonnet 5 | $0.00006 | $0.00423 |
| Haiku 4.5 | $0.00003 | $0.00212 |
Grade A, and why
fortigate 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the USAP Fintech FortiGate Zero-Day Challenge against cs-security-analyst.
Step 1 — Load Main Agent
Read agents/security/cs-security-analyst.md in full using the Read tool.
Adopt the full Alex persona (Tier 2 SOC, 12y experience). You are now operating under two active workflows simultaneously:
- AT — Alert Triage (classify and prioritise the zero-day alert)
- CA — Compromise Assessment (determine whether the firewall is already owned)
Do not break persona until this command completes.
Step 2 — Load Scenario
Read tests/scenarios/fintech-fortigate-zero-day.json in full.
Key constraints from the scenario — internalize these before producing any output:
- Production cannot be shut down
- No vendor patch available for 7 days
- Attacker is confirmed aware of the vulnerability
- Exploit completes in 3 minutes — SIEM 5-min batch polling creates a detection blind window
- Five UNKNOWN fields must be labeled
PREREQUISITE_UNVERIFIED— do NOT assume values:tls_inspection_statusaws_imds_versionfirewall_cpu_baselinesiem_eps_capacityexisting_compromise_status← critical: do not assume the firewall is clean
Step 3 — Apply AT Workflow: Alert Triage
Apply the AT (Alert Triage) reasoning procedure to this scenario.
Produce:
- Alert classification and priority (SEV-1 or SEV-2 — justify)
- Top detection signals available given 5-min SIEM gap and no IDS signature
- Telemetry quality assessment — flag the 5-minute blind window as a structural gap
- Noise suppression assessment (no DDoS smokescreen in this scenario — note that)
Step 4 — Apply CA Workflow: Compromise Assessment
Apply the CA (Compromise Assessment) reasoning procedure.
Critical gate: existing_compromise_status is UNKNOWN. You MUST NOT assert the firewall is clean. Produce a compromise assessment with:
- Confidence score (0.0–1.0)
- Indicators to check (what forensic artifacts would confirm or deny compromise)
- Recommended verification steps expressed as USAP intent blocks only — no raw CLI
- Assessment outcome: UNKNOWN / LIKELY_CLEAN / LIKELY_COMPROMISED / CONFIRMED_COMPROMISED
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.
- 10d ago First seen · 208 lines · 31 tokens per session scan A 00e35ac9b934
fortigate is a command published in the GitHub repository jaskaranhundal/usap-skills (4 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 2,115 once invoked, about $0.0002 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.