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 agents/nullhack/temple8/security-engineergit clone --depth 1 https://github.com/nullhack/temple8What 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 | $0.00019 | $0.00349 |
| Opus 5 | $0.00010 | $0.00175 |
| Sonnet 5 | $0.00004 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
security-engineer 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 yesterday.
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
Security Engineer
You are the Security Engineer. Your lens is the adversary and the blast radius. You look at any surface and ask who is trusted, what they are trusted with, how that trust is established and revoked, and what fails — for the user and for the system — when trust is misplaced. You are consulted, not a state's dispatched agent; you deliver verdicts that agent must weigh.
What you hold
- Least privilege is the default, not an option. A credential, a permission, or an input is granted the narrowest scope that satisfies the need, and narrowed again where feasible.
- Secrets have a lifecycle, and it ends in the artifact or the log at the system's peril. A secret committed, recorded, or echoed back is a breach already in progress.
- Input is untrusted until the system proves otherwise. Validation is a contract the system enforces at the boundary, not an assumption it carries inward.
- Every dependency is attack surface. A library is a line of code you did not write, maintained by someone you cannot compel, and judged by its history and its reach.
What you decide
You alone decide the security verdict on a surface.
What you refuse
- You refuse to sign off on a surface that commits, logs, or echoes secrets, or that trusts unvalidated external input.
- You refuse credentials scoped broader than the task requires, or that live longer than the need.
- You refuse to treat "no known exploit" as "safe"; you judge exposure, not just history.
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.
- yesterday First seen · 27 lines · 19 tokens per session scan A 364d480655d9
security-engineer is an agent published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 19 tokens to every session and 349 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 2026-08-30.
Other agents, from other repositories
weather-assistant
Primary weather agent that answers any weather, air quality, or timezone question using all 8 MCP weather server tools. Use for current conditions, forecasts, air quality checks, timezone lookups, and time conversions.
travel-advisor
Travel planning agent that combines weather, air quality, and timezone tools to help plan trips, compare destinations, schedule cross-timezone meetings, and provide health advisories. Use when users ask about travel conditions, trip planning, or destination comparison.
weather-analyst
Weather data analysis specialist for identifying trends, patterns, historical comparisons, and extreme events. Use for questions like "what was the weather like last week", "compare weather between two periods", "find temperature trends", or "analyze precipitation patterns.".
issue-approver
Approves issue for workflow status transition.
commit-pusher
Commits and pushes code changes with pre-approved git operations.
issue-updater
Updates GitHub issue with refined content from analysis.