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.
npx skills add Servosity/msp-skills --skill fortinetgit clone --depth 1 https://github.com/Servosity/msp-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/skills/servosity/msp-skills/fortinet)<a href="https://agentmods.dev/skills/servosity/msp-skills/fortinet"><img src="https://agentmods.dev/badge/skills/servosity/msp-skills/fortinet/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/skills/servosity/msp-skills/fortinet"><img src="https://agentmods.dev/badge/skills/servosity/msp-skills/fortinet.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 | $0.00149 | $0.10454 |
| Opus 5.5 | $0.00060 | $0.04182 |
| Sonnet 5.5 | $0.00030 | $0.02091 |
| Haiku 4.5 | $0.00015 | $0.01045 |
Grade B, and why
fortinet scanned grade B with 3 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 today.
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.
Tells the agent never to refusemediumAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
| `file:<path>` | Atomically write output to `<path>` (tmp + rename). Binary-response commands write decoded payload bytes (not the base64 JSON envelope) and print a small JSON receipt on stdout; `--json`/`--csv` do not Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Each FortiGate uses its own REST API administrator token (System > Administrators > Create New > REST API Admin, or `execute api-user generate-key <name>`), sent as `Authorization: Bearer`; your source IP must be one of Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/fortinet/install.sh) The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 599 B
- AGENTS.md 9.2 KB
- CHANGELOG.md 2.7 KB
- cli/.golangci.yml 555 B
- cli/cmd/fortinet-cli/main.go 407 B
- cli/cmd/fortinet-mcp/http_auth_test.go 4.7 KB
- cli/cmd/fortinet-mcp/main.go 6.2 KB
- cli/go.mod 1.0 KB
- cli/go.sum 7.9 KB
- cli/internal/cache/cache.go 1.8 KB
- cli/internal/cli/address_groups_get.go 4.7 KB
- cli/internal/cli/address_groups_list.go 4.5 KB
- cli/internal/cli/address_groups.go 771 B
- cli/internal/cli/addresses_get.go 4.7 KB
- cli/internal/cli/addresses_list.go 4.5 KB
- cli/internal/cli/addresses.go 749 B
- cli/internal/cli/admin_profiles_get.go 4.5 KB
- cli/internal/cli/admin_profiles_list.go 4.3 KB
- cli/internal/cli/admin_profiles.go 771 B
- cli/internal/cli/administrators_get.go 4.5 KB
- cli/internal/cli/administrators_list.go 4.3 KB
- cli/internal/cli/administrators.go 774 B
- cli/internal/cli/agent_context.go 7.9 KB
- cli/internal/cli/analytics.go 6.0 KB
- cli/internal/cli/api_discovery.go 3.7 KB
- cli/internal/cli/api_users_get.go 4.5 KB
- cli/internal/cli/api_users_list.go 4.3 KB
- cli/internal/cli/api_users.go 746 B
- cli/internal/cli/audit_admins_test.go 1.1 KB
- cli/internal/cli/audit_admins.go 2.7 KB
- cli/internal/cli/audit_firmware_test.go 1.1 KB
- cli/internal/cli/audit_firmware.go 3.5 KB
- cli/internal/cli/audit_licenses_test.go 1.1 KB
- cli/internal/cli/audit_licenses.go 4.1 KB
- cli/internal/cli/audit_sslvpn_test.go 1.1 KB
- cli/internal/cli/audit_sslvpn.go 3.8 KB
- cli/internal/cli/audit.go 1.1 KB
- cli/internal/cli/auth.go 8.6 KB
- cli/internal/cli/channel_workflow.go 8.4 KB
- cli/internal/cli/data_source.go 52 KB
- cli/internal/cli/deliver_download_test.go 1.8 KB
- cli/internal/cli/deliver.go 5.1 KB
- cli/internal/cli/dhcp_servers_get.go 4.7 KB
- cli/internal/cli/dhcp_servers_list.go 4.5 KB
- cli/internal/cli/dhcp_servers.go 761 B
- cli/internal/cli/doctor_verdict.go 3.1 KB
- cli/internal/cli/doctor.go 33 KB
- cli/internal/cli/export_perms_test.go 1.1 KB
- cli/internal/cli/export.go 7.2 KB
- cli/internal/cli/feedback.go 6.8 KB
- cli/internal/cli/fleet_audit_test.go 1.1 KB
- cli/internal/cli/fleet_audit.go 12 KB
- cli/internal/cli/fleet_changes_test.go 1.1 KB
- cli/internal/cli/fleet_changes.go 7.5 KB
- cli/internal/cli/fleet_health_test.go 1.1 KB
- cli/internal/cli/fleet_health.go 6.8 KB
- cli/internal/cli/fleet.go 1011 B
- cli/internal/cli/fortinet_audit_core.go 11 KB
- cli/internal/cli/fortinet_cloud.go 5.7 KB
- cli/internal/cli/fortinet_fleet_test.go 34 KB
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.
- today First seen · 719 lines · 149 tokens per session scan B c547d2eb5848
fortinet is a skill published in the GitHub repository Servosity/msp-skills (59 stars, last pushed today), with no licence file. It adds 149 tokens to every session and 10,454 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it B with 3 findings (tells the agent never to refuse, asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other skills, from other repositories
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.
laboneq-control
An offline compiler for turning structured pulse descriptions into Zurich Instruments HDAWG sequencer code and simulated output waveforms. It does not connect to instruments or model the resulting quantum dynamics.
qblox-scheduling
An offline pulse scheduler that builds timed square-wave sequences and sampled envelopes. A pulse is a time-varying control signal; this tool represents its timing and samples its mathematical shape without controlling an instrument.
qctrl-workbench
A builder for single-qubit control graphs and a reader for the status of existing Q-CTRL Boulder Opal or Fire Opal jobs. It can prepare a serialized graph locally and, when explicitly enabled with credentials, make one remote status query.
qililab-control
An offline compiler that converts timed I/Q square pulses and waits into Qblox Q1ASM instructions and waveform tables. I/Q means the two signal components used to control a device; the compiler does not connect to instruments or run an experiment.
qua-programs
A local generator for Quantum Machines QUA pulse programs for one OPX1 analogue output. It produces source code, configuration, and encoded program data for constant-voltage pulses, but does not run them or simulate hardware.