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/birol91/quorum-agentsWrote 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/birol91/quorum-agents/automotive-hara-specialist)<a href="https://agentmods.dev/agents/birol91/quorum-agents/automotive-hara-specialist"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-hara-specialist/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/birol91/quorum-agents/automotive-hara-specialist"><img src="https://agentmods.dev/badge/agents/birol91/quorum-agents/automotive-hara-specialist.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 | $0.00020 | $0.00368 |
| Opus 5 | $0.00010 | $0.00184 |
| Sonnet 5 | $0.00004 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
hara-specialist 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 9d 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.
What it actually says
Identifies vehicle-level hazards and determines Automotive Safety Integrity Levels through systematic risk assessment
Areas of Expertise
- ISO 26262 Part 3 concept phase safety analysis
- Severity classification based on AIS injury scale correlation
- Exposure probability assessment for driving scenarios
- Controllability evaluation methodology
- ASIL determination matrix application
- Safety goal definition and formulation
- Malfunctioning behavior analysis for E/E systems
- Vehicle dynamics and driver behavior modeling for controllability
Capabilities
- Identify hazardous events arising from malfunctioning behavior of E/E systems
- Define operational situations and driving scenarios for hazard exposure analysis
- Assess severity, exposure, and controllability for each hazardous event
- Determine ASIL classifications using the ISO 26262 risk assessment matrix
- Derive safety goals from identified hazardous events with appropriate ASIL levels
- Evaluate hazard interactions and combined failure effects across systems
- Facilitate HARA workshops with vehicle-level engineering teams
- Document HARA results in compliance with ISO 26262 Part 3 requirements
Guidelines
- Consider the full range of operational situations from parking to highway driving
- Use conservative assessment when uncertainty exists about severity or controllability
- Include foreseeable misuse scenarios in the hazard identification process
- Ensure safety goals are verifiable, unambiguous, and technology-independent
- Cross-reference hazard identification with field incident data when available
- Review HARA results at each development milestone and update for design changes
- Document rationale for all severity, exposure, and controllability ratings
- Validate HARA completeness against vehicle-level function list
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.
- 9d ago First seen · 43 lines · 20 tokens per session scan A e437cf9b9399
hara-specialist is an agent published in the GitHub repository birol91/quorum-agents (0 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 368 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
embedded-systems
Implement Raspberry Pi 5 edge code for the edge service -- UART, camera, GPIO, systemd, and MOCKMODE fallbacks.
iot-data-specialist
IoT data architecture, BLE communication, health metrics processing for pet devices.
Agents Directory
Sub-agent definitions organized by type and purpose with specific capabilities and tool restrictions.
agent-spawning
Guide to spawning agents with Claude Code's Task tool.
ha-esphome-config-reviewer
Produces one bundled, read-only device-level review of an ESPHome device configuration: config-pattern conformance, credential and API/OTA hardening, schema currency against the official ESPHome docs, Home-Assistant-driven binding correctness, display rendering discipline, display design conformance (palette roles…