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 agentmods add skills/x3allamerican/skills/csa-basic-threshold-differencesnpx skills add x3allamerican/skills --skill csa-basic-threshold-differencesgit clone --depth 1 https://github.com/x3allamerican/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/x3allamerican/skills/csa-basic-threshold-differences)<a href="https://agentmods.dev/skills/x3allamerican/skills/csa-basic-threshold-differences"><img src="https://agentmods.dev/badge/skills/x3allamerican/skills/csa-basic-threshold-differences.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00692 |
| Opus 5 | $0.00023 | $0.00346 |
| Sonnet 5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
csa-basic-threshold-differences 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 3d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BASIC Threshold Differences: General Freight vs Hazmat vs Passenger
The CSA Safety Measurement System (SMS) sets different intervention thresholds depending on what the carrier hauls. Same BASIC score can be alert-level for one carrier and clean for another.
Threshold table
| Carrier type | Unsafe Driving | HOS Compliance | Driver Fitness | Controlled Substances | Vehicle Maintenance | Hazmat Compliance | Crash Indicator |
|---|---|---|---|---|---|---|---|
| General freight | 65th | 65th | 80th | 80th | 80th | N/A | 65th |
| Hazmat carrier | 60th | 60th | 75th | 75th | 75th | 60th | 60th |
| Passenger carrier | 50th | 50th | 65th | 65th | 65th | N/A | 50th |
Why the difference
- Hazmat carriers handle materials that can harm public — tighter safety expected
- Passenger carriers carry humans — tighter safety expected
- General freight is property-only — wider tolerance
What "alert threshold" means
- BASIC at or above the threshold percentile = alert
- Triggers FMCSA intervention prioritization
- Combined with crash history can trigger Compliance Review
How peer groups work
FMCSA assigns each carrier to a peer group based on:
- Number of power units (vehicles)
- Inspection volume
- Time in operation
Peer group = pool of similar carriers. Your BASIC percentile is relative to your peer group.
Implications for owner-operator vs fleet
- 1-truck owner-operator: smaller peer group, more volatile percentile
- 50-truck fleet: larger peer group, more stable percentile
- 100+ truck fleet: largest peer group, most stable
Compass dashboard view
Compass CSA module shows your BASIC scores and the relevant threshold for your carrier type. Alert flags trigger when within 5 percentile points of threshold.
CFR citations
- 49 CFR § 385.4
- FMCSA SMS Methodology
How Compass surfaces this
Searchable in Compass Ask. Runs against the carrier's actual fleet data when invoked from the relevant tracker. Read-only; no actions without explicit user approval.
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.
- 3d ago First seen · 62 lines · 45 tokens per session scan A ca1eb909653a
csa-basic-threshold-differences is a skill published in the GitHub repository x3allamerican/skills (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 692 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 skills, from other repositories
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
sensitive-data
Rosetta CRITICAL MUST skill. MUST activate when you suspect, there is a slight chance, encounter, read, process, or are about to output any sensitive or possibly sensitive data including PII, PCI, HIPAA, PHI, GDPR, SOC2, FedRAMP, secrets, API keys, passwords, credentials, tokens, certificates, or any data that could…
healthcare-providers-verify
Validates practitioner credentials and license status against the NPI registry. Cross-references specialties, credentials, and practice addresses against official records. Returns Verified / Partially Verified / Unverified / Flagged per practitioner with mismatch details and source URLs. Triggers: "verify these…
telnyx-email-suppressions-curl
Manage email suppressions (blocks), import and export suppression lists, and manage unsubscribe groups. Use for deliverability compliance and bounce handling.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices". Focuses on visual design and interaction patterns. Do NOT use for performance audits (use core-web-vitals), SEO (use seo), or…
patent-review
Multi-round cyclic rigorous review of Chinese patent technical disclosure documents. Supports multi-dimension review (data flow closure, terminology consistency, state transition, formula completeness, error code routing, text-diagram consistency), round-by-round convergence, and optional auto-fix (default off, severe…