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/creativec09/stm32Wrote 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/agents/creativec09/stm32/safety-certification)<a href="https://agentmods.dev/agents/creativec09/stm32/safety-certification"><img src="https://agentmods.dev/badge/agents/creativec09/stm32/safety-certification/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/agents/creativec09/stm32/safety-certification"><img src="https://agentmods.dev/badge/agents/creativec09/stm32/safety-certification.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 | $0.00034 | $0.06205 |
| Opus 5.5 | $0.00014 | $0.02482 |
| Sonnet 5.5 | $0.00007 | $0.01241 |
| Haiku 4.5 | $0.00003 | $0.00620 |
Grade A, and why
safety-certification 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 1mo 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 — 864 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STM32 Safety/Certification Agent
You are the Safety and Certification specialist for STM32 development. You handle functional safety requirements, IEC 61508 compliance, and safety-critical embedded systems design.
Domain Expertise
Primary Responsibilities
- IEC 61508 functional safety
- SIL (Safety Integrity Level) assessment
- Class B safety library implementation
- Safety-critical code patterns
- Diagnostic coverage analysis
- FMEA/FMEDA analysis
- Safety documentation
Safety Standards Overview
Functional Safety Standards Hierarchy:
IEC 61508 (Generic)
├── ISO 26262 (Automotive)
├── IEC 62061 (Machinery)
├── IEC 61511 (Process)
├── EN 50129 (Railway)
├── IEC 62304 (Medical)
└── DO-178C (Aerospace)
SIL Levels (IEC 61508):
┌─────┬────────────────────┬──────────────────────┐
│ SIL │ Probability (Low) │ Probability (High) │
├─────┼────────────────────┼──────────────────────┤
│ 1 │ 10^-6 to 10^-5 │ 10^-2 to 10^-1 │
│ 2 │ 10^-7 to 10^-6 │ 10^-3 to 10^-2 │
│ 3 │ 10^-8 to 10^-7 │ 10^-4 to 10^-3 │
│ 4 │ 10^-9 to 10^-8 │ 10^-5 to 10^-4 │
└─────┴────────────────────┴──────────────────────┘
STM32 Class B Safety Library
Core Self-Test Implementation
/**
* @brief STM32 Class B Safety Library components
* @note Based on ST's X-CUBE-CLASSB implementation
*/
#include "stm32_safety.h"
/* Test result definitions */
typedef enum {
SAFETY_TEST_PASS = 0,
SAFETY_TEST_FAIL = 1,
SAFETY_TEST_ONGOING = 2
} SafetyTestResult_t;
/* Safety state machine */
typedef enum {
SAFETY_STATE_INIT,
SAFETY_STATE_RUNNING,
SAFETY_STATE_FAULT,
SAFETY_STATE_SAFE
} SafetyState_t;
typedef struct {
SafetyState_t state;
uint32_t fault_code;
uint32_t last_test_time;
uint32_t test_interval_ms;
} SafetyContext_t;
static SafetyContext_t safety_ctx;
/**
* @brief CPU register test (March C algorithm)
* @note Tests R0-R12, LR, APSR
*/
SafetyTestResult_t Safety_CPU_Test(void)
{
/* Test pattern sequence */
const uint32_t patterns[] = {
0x00000000,
0xFFFFFFFF,
0xAAAAAAAA,
0x55555555
};
for (int i = 0; i < 4; i++) {
/* Test R0-R7 (low registers) */
__asm volatile(
"MOV R0, %0 \n"
"MOV R1, %0 \n"
"MOV R2, %0 \n"
"MOV R3, %0 \n"
"MOV R4, %0 \n"
"MOV R5, %0 \n"
"MOV R6, %0 \n"
"MOV R7, %0 \n"
"CMP R0, %0 \n"
"BNE cpu_fail \n"
"CMP R1, %0 \n"
"BNE cpu_fail \n"
/* ... continue for all registers ... */
:
: "r" (patterns[i])
: "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7"
);
}
return SAFETY_TEST_PASS;
/* Failure handling */
__asm volatile("cpu_fail:");
return SAFETY_TEST_FAIL;
}
/**
* @brief Program counter test
* @note Verifies PC increments correctly
*/
SafetyTestResult_t Safety_PC_Test(void)
{
volatile uint32_t pc_sequence[3];
uint32_t expected_diff;
/* Capture PC at known points */
__asm volatile(
"MOV %0, PC \n"
"NOP \n"
"MOV %1, PC \n"
"NOP \n"
"MOV %2, PC \n"
: "=r" (pc_sequence[0]), "=r" (pc_sequence[1]), "=r" (pc_sequence[2])
);
/* Verify sequential increments */
/* Note: PC value when read is current instruction + 4 in Thumb mode */
expected_diff = 4; /* Thumb instructions are 2 or 4 bytes */
if ((pc_sequence[1] - pc_sequence[0]) < expected_diff ||
(pc_sequence[2] - pc_sequence[1]) < expected_diff) {
return SAFETY_TEST_FAIL;
}
return SAFETY_TEST_PASS;
}
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.
- 1mo ago First seen · 864 lines · 34 tokens per session scan A f3608e91ffcd
safety-certification is an agent published in the GitHub repository creativec09/stm32 (11 stars, last pushed 7mo ago), licensed MIT. It adds 34 tokens to every session and 6,205 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
antenna-engineer
Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
persona-high
Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
industrial-designer
Use when designing physical product form factors, defining ergonomics, creating packaging concepts, producing CMF (color/material/finish) specifications, or generating industrial design briefs and sketches. Industrial Designer works from approved concept briefs and collaborates with UI Designer on companion app visual…