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 pangzhenying2025/hermes-automotive-skills --skill automotive-diagnosticsgit clone --depth 1 https://github.com/pangzhenying2025/hermes-automotive-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/pangzhenying2025/hermes-automotive-skills/automotive-diagnostics)<a href="https://agentmods.dev/skills/pangzhenying2025/hermes-automotive-skills/automotive-diagnostics"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/automotive-diagnostics/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/pangzhenying2025/hermes-automotive-skills/automotive-diagnostics"><img src="https://agentmods.dev/badge/skills/pangzhenying2025/hermes-automotive-skills/automotive-diagnostics.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 | $0.00039 | $0.38180 |
| Opus 5 | $0.00019 | $0.19090 |
| Sonnet 5 | $0.00008 | $0.07636 |
| Haiku 4.5 | $0.00004 | $0.03818 |
Grade B, and why
automotive-diagnostics scanned grade B with 1 finding 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 12d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo make install How it starts
The opening of the file, as written. The whole thing — 4,935 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automotive Diagnostics
Diagnostic Tooling
Diagnostic Tooling - CANoe, CAPL, ODXStudio
Overview
Professional automotive diagnostic tools include CANoe/CANalyzer for testing, CAPL for scripting, ODXStudio for database creation, and open-source alternatives. This skill covers tooling ecosystems and DIY diagnostic development.
Vector CANoe/CANalyzer
CANoe Features
- Network simulation and testing
- ECU testing and validation
- Diagnostic protocol support (UDS, OBD-II, DoIP)
- CAPL scripting for automation
- Test automation frameworks
CAPL (Communication Access Programming Language)
CAPL Script Example - Automated Diagnostic Test:
/*
* CAPL Script: Automated UDS Diagnostic Test
* Tests: Session control, DTC reading, parameter reading
*/
includes
{
#include "DiagnosticLibrary.cin"
}
variables
{
int gTestsPassed = 0;
int gTestsFailed = 0;
int gTestTimeout = 2000; // ms
// Diagnostic addresses
const dword kTesterAddress = 0x7E0;
const dword kECUAddress = 0x7E8;
// Test results
char gTestReport[1000];
}
/* Initialize test environment */
on start
{
write("========================================");
write("UDS Diagnostic Test Suite");
write("========================================");
// Initialize diagnostic session
DiagInit(kTesterAddress, kECUAddress);
// Start test sequence
setTimer(tmrStartTests, 100);
}
/* Test 1: Extended Diagnostic Session */
on timer tmrStartTests
{
write("\n[Test 1] Extended Diagnostic Session");
// Build UDS request: 0x10 0x03
byte request[2];
request[0] = 0x10; // DiagnosticSessionControl
request[1] = 0x03; // Extended session
// Send diagnostic request
DiagSendRequest(request, 2);
// Wait for response
setTimer(tmrTest1Response, gTestTimeout);
}
/* Handle Test 1 Response */
on timer tmrTest1Response
{
byte response[100];
int length;
if (DiagReceiveResponse(response, length))
{
if (response[0] == 0x50 && response[1] == 0x03)
{
write(" [PASS] Extended session activated");
gTestsPassed++;
// Start next test
setTimer(tmrTest2, 100);
}
else if (response[0] == 0x7F)
{
write(" [FAIL] Negative response: 0x%02X", response[2]);
gTestsFailed++;
TestFailed();
}
else
{
write(" [FAIL] Invalid response format");
gTestsFailed++;
TestFailed();
}
}
else
{
write(" [FAIL] Timeout waiting for response");
gTestsFailed++;
TestFailed();
}
}
/* Test 2: Read DTCs */
on timer tmrTest2
{
write("\n[Test 2] Read Diagnostic Trouble Codes");
// Build UDS request: 0x19 0x02 0xFF
byte request[3];
request[0] = 0x19; // ReadDTCInformation
request[1] = 0x02; // reportDTCByStatusMask
request[2] = 0xFF; // All status masks
DiagSendRequest(request, 3);
setTimer(tmrTest2Response, gTestTimeout);
}
/* Handle Test 2 Response */
on timer tmrTest2Response
{
byte response[100];
int length;
int i, dtcCount;
if (DiagReceiveResponse(response, length))
{
if (response[0] == 0x59 && response[1] == 0x02)
{
// Parse DTC count (after status availability mask)
dtcCount = (length - 4) / 4;
write(" [PASS] Read %d DTCs", dtcCount);
// Parse and display DTCs
for (i = 0; i < dtcCount; i++)
{
int offset = 4 + i * 4;
char dtc[10];
ParseDTC(response[offset], response[offset+1], response[offset+2], dtc);
byte status = response[offset+3];
write(" DTC: %s, Status: 0x%02X", dtc, status);
}
gTestsPassed++;
setTimer(tmrTest3, 100);
}
else if (response[0] == 0x7F)
{
write(" [FAIL] Negative response: 0x%02X", response[2]);
gTestsFailed++;
TestFailed();
}
}
else
{
write(" [FAIL] Timeout");
gTestsFailed++;
TestFailed();
}
}
/* Test 3: Read Data by Identifier (VIN) */
on timer tmrTest3
{
write("\n[Test 3] Read VIN (DID 0xF190)");
byte request[3];
request[0] = 0x22; // ReadDataByIdentifier
request[1] = 0xF1; // DID high byte
request[2] = 0x90; // DID low byte
DiagSendRequest(request, 3);
setTimer(tmrTest3Response, gTestTimeout);
}
/* Handle Test 3 Response */
on timer tmrTest3Response
{
byte response[100];
int length;
char vin[18];
if (DiagReceiveResponse(response, length))
{
if (response[0] == 0x62 && response[1] == 0xF1 && response[2] == 0x90)
{
// Extract VIN (17 characters)
int i;
for (i = 0; i < 17; i++)
{
vin[i] = response[3 + i];
}
vin[17] = 0; // Null terminate
write(" [PASS] VIN: %s", vin);
gTestsPassed++;
// Complete test suite
setTimer(tmrTestComplete, 100);
}
else if (response[0] == 0x7F)
{
write(" [FAIL] Negative response: 0x%02X", response[2]);
gTestsFailed++;
TestFailed();
}
}
else
{
write(" [FAIL] Timeout");
gTestsFailed++;
TestFailed();
}
}
/* Test Suite Complete */
on timer tmrTestComplete
{
write("\n========================================");
write("Test Suite Complete");
write(" Tests Passed: %d", gTestsPassed);
write(" Tests Failed: %d", gTestsFailed);
write("========================================");
if (gTestsFailed == 0)
{
write("RESULT: ALL TESTS PASSED");
}
else
{
write("RESULT: SOME TESTS FAILED");
}
}
/* Handle test failure */
void TestFailed()
{
setTimer(tmrTestComplete, 100);
}
/* Parse DTC bytes to string format */
void ParseDTC(byte high, byte mid, byte low, char dtc[10])
{
byte system = (high >> 6) & 0x03;
byte digit1 = (high >> 4) & 0x03;
byte digit2 = high & 0x0F;
byte digit3 = (mid >> 4) & 0x0F;
byte digit4 = mid & 0x0F;
char systemChar;
switch (system)
{
case 0: systemChar = 'P'; break;
case 1: systemChar = 'C'; break;
case 2: systemChar = 'B'; break;
case 3: systemChar = 'U'; break;
}
snprintf(dtc, 10, "%c%d%X%X%X", systemChar, digit1, digit2, digit3, digit4);
}
/* Diagnostic helper functions */
void DiagInit(dword tester, dword ecu)
{
// Initialize diagnostic addressing
write("Initializing diagnostic session");
write(" Tester: 0x%03X", tester);
write(" ECU: 0x%03X", ecu);
}
void DiagSendRequest(byte request[], int length)
{
// Send diagnostic request via CAN
message * msg;
int i;
msg = {CAN, kTesterAddress, 0, 8};
// Build ISO-TP single frame or multi-frame message
if (length <= 7)
{
// Single frame
msg.byte(0) = 0x00 | length;
for (i = 0; i < length; i++)
{
msg.byte(i + 1) = request[i];
}
output(msg);
}
else
{
// Multi-frame (simplified - full implementation needed)
write(" Sending multi-frame request");
}
}
int DiagReceiveResponse(byte response[], int &length)
{
// Simplified - actual implementation needs ISO-TP handling
// This would be called from on message handler
return 0;
}
What ships with it
1 file 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.
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.
- 12d ago First seen · 4,935 lines · 39 tokens per session scan B 3b593b16da77
automotive-diagnostics is a skill published in the GitHub repository pangzhenying2025/hermes-automotive-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 38,180 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
iso26262
ISO 26262 functional-safety expert that operates in two modes: (1) HARA / ASIL determination — enumerate hazardous events from item malfunctions × driving situations, rate Severity (S0–S3), Exposure (E0–E4), Controllability (C0–C3), look up ASIL from ISO 26262-3:2018 Table 4, and produce a HARA report with Safety…
automotive-syseng
When the user wants to analyze automotive requirements, check INCOSE/EARS compliance, review MISRA-C code, assess ADAS levels, or verify ISO 26262/AUTOSAR/SOTIF conformance. Also use when the user says 'check requirements', 'EARS check', 'INCOSE analysis', 'MISRA check', 'ASIL assessment', 'V-model check'…
automotive-expert
Expert-level automotive systems, connected vehicles, fleet management, telematics, ADAS, and automotive software. Use when the user mentions connected car, fleet, telematics, ADAS, or vehicle, or when the task involves Automotive Systems, Technologies, Standards and Protocols, or Fleet Management.
embedded-debugging
Senior embedded debugging expert. Defaults to Classic AUTOSAR on ARM Cortex-M/R targets and operates in two modes: (1) Problem-report triage — take a field PR / bug ticket and produce symptom classification, affected-element mapping, ranked hypotheses, data-collection plan, and step-by-step investigation; (2) Targeted…
diagnose-battery-charging-problem
Use when a vehicle has starting problems, battery warning lights, or electrical symptoms — systematically testing battery condition, alternator output, and charging circuit integrity to identify the root cause before replacing components.
diagnose-electrical-fault
Use when a vehicle has a blown fuse, inoperative accessory, warning light, or intermittent electrical failure — applying a systematic test sequence (visual, OBD-II codes, voltage/continuity testing) to isolate the fault to a specific component or circuit without replacing parts blindly.