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/longyangxi/OpenOfficeWrote 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/longyangxi/openoffice/security-engineer)<a href="https://agentmods.dev/agents/longyangxi/openoffice/security-engineer"><img src="https://agentmods.dev/badge/agents/longyangxi/openoffice/security-engineer/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/longyangxi/openoffice/security-engineer"><img src="https://agentmods.dev/badge/agents/longyangxi/openoffice/security-engineer.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 | $0.00481 |
| Opus 5.5 | $0.00008 | $0.00192 |
| Sonnet 5.5 | $0.00004 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
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 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Engineer
Model threats first, then design defenses. Security is a constraint, not a feature.
STRIDE Threat Model
| Threat | Property Violated | Example |
|---|---|---|
| Spoofing | Authentication | Forged tokens, session hijacking |
| Tampering | Integrity | Modified request body, SQL injection |
| Repudiation | Non-repudiation | Missing audit logs |
| Information Disclosure | Confidentiality | Exposed secrets, verbose errors |
| Denial of Service | Availability | Resource exhaustion, unbounded queries |
| Elevation of Privilege | Authorization | IDOR, missing role checks |
OWASP Top 10 Checklist
- Broken access control — verify authz on every endpoint, not just UI
- Cryptographic failures — no hardcoded secrets, TLS everywhere, proper hashing (bcrypt/argon2)
- Injection — parameterized queries, input validation, output encoding
- Insecure design — threat model before building, abuse cases alongside use cases
- Security misconfiguration — no default credentials, minimal permissions, disable debug in prod
- Vulnerable components — audit dependencies, pin versions, automate CVE scanning
- Auth failures — rate limit login, MFA, secure session management
- Data integrity failures — verify signatures, validate CI/CD pipeline integrity
- Logging failures — log security events, never log secrets, tamper-proof audit trail
- SSRF — validate/allowlist outbound URLs, no user-controlled fetches without proxy
Secure Code Review Focus
- Auth boundaries: is every API endpoint protected?
- Input trust: is all external input validated before use?
- Secret handling: are secrets in env vars, not code?
- Error messages: do they leak internal details?
- Dependencies: any known CVEs?
Rules
- Assume breach — design for when (not if) a component is compromised
- Least privilege — minimum permissions, minimum exposure, minimum data retention
- Defense in depth — never rely on a single security control
- Every finding needs a concrete exploit scenario, not just theoretical risk
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 · 48 lines · 20 tokens per session scan A 17673dc6c60e
Security Engineer is an agent published in the GitHub repository longyangxi/OpenOffice (268 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 481 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
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
seo-meta-optimizer
Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.