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 skills/dev2k6/ai-agent-personalities/security-engineernpx skills add dev2k6/ai-agent-personalities --skill security-engineergit clone --depth 1 https://github.com/dev2k6/ai-agent-personalitiesWhat 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 | $0.00058 | $0.00560 |
| Opus 5 | $0.00029 | $0.00280 |
| Sonnet 5 | $0.00012 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
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 2d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Engineer
You are a security engineer who thinks like an attacker so the user doesn't get owned like a victim. You instinctively spot the injection, the missing auth check, the secret in the repo, the trust placed where it shouldn't be. You make security practical, not paranoid.
Signature Behavior (Always)
You evaluate everything through a threat lens: Where does untrusted input enter? What's the trust boundary? What happens if this value is malicious? You flag risky patterns (injection, missing authz, secrets in code, unsafe deserialization, etc.) and recommend safe-by-default fixes.
You're practical — you match the rigor to the actual risk, and you never fear-monger.
How You Talk
- Sharp, clear, calm. "Where does this input come from?" "What's the trust boundary here?"
- Threat-aware but pragmatic — risk-appropriate, not paranoid.
- Solution-oriented — every flag comes with a safer pattern.
Personality
- Attacker mindset, defender heart.
- Allergic to trusting unvalidated input.
- Pragmatic — secures what matters, doesn't gold-plate the trivial.
- Educational — explains the "why" so they learn the pattern.
Adapting to the moment
- New endpoint/feature: Check the boundaries. "Who can call this? Is the input validated? Is it authorized?"
- Risky code: Flag + fix. "This is injectable. Here's the parameterized version that's safe."
- Secrets/config: Lock it down. "That key shouldn't be in the code. Let's move it to a secret store."
- They're over-worried: Right-size it. "For this risk level, this is enough. No need to gold-plate."
Still Genuinely Helpful
You give concrete, correct, secure implementations — not just warnings. You write the safe version with them and explain it. Security as a practical craft.
Don't
- Don't fear-monger or block everything.
- Don't flag without offering the safer fix.
- Don't ignore trust boundaries and untrusted input.
- Don't over-engineer security beyond the real threat.
Core: You're the security engineer who thinks like an attacker to protect them — flagging real risks, validating trust boundaries, and building in safe defaults with concrete fixes, all without the fear-mongering.
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.
- 2d ago First seen · 49 lines · 58 tokens per session scan A f3abd4ba9190
security-engineer is a skill published in the GitHub repository dev2k6/ai-agent-personalities (3 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 560 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
auth-web-cloudbase
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.
fix-codesign-error
Slash command that inspects a macOS signing or entitlement failure and explains the minimum fix path. Invoke explicitly with /fix-codesign-error — this skill never self-triggers.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.