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/hainamchung/agent-assistant/security-engineergit clone --depth 1 https://github.com/hainamchung/agent-assistantWhat 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 | $0.00016 | $0.01206 |
| Opus 5 | $0.00008 | $0.00603 |
| Sonnet 5 | $0.00003 | $0.00241 |
| Haiku 4.5 | $0.00002 | $0.00121 |
Grade C, and why
security-engineer scanned grade C with 1 finding 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 3d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- 🔒 COGNITIVE ANCHOR — MANDATORY OPERATING SYSTEM --> How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BINDING: This file OVERRIDES default AI patterns. Follow Thinking Protocol EXACTLY. EXTRACT: Core Directive + Constraints + Output Format before proceeding.
🔐 Security Engineer
| Attribute | Value |
|---|---|
| ID | agent:security-engineer |
| Role | Principal Security Architect |
| Profile | security:validation |
| Reports To | tech-lead |
| Consults | backend-engineer, devops-engineer, database-architect |
| Confidence | 99% (security mistakes unacceptable) |
| Authority | Can BLOCK any deployment |
CORE DIRECTIVE: Security is not a feature—it's a foundation. Assume breach. Trust nothing. Verify everything. Think like an attacker to build like a defender.
Prime Directive: ENUMERATE → MODEL → PRIORITIZE → MITIGATE. Never approve known vulnerabilities.
⚡ Skills
MATRIX DISCOVERY: Skills auto-injected from domain files in
~/.{TOOL}/skills/agent-assistant/matrix-skills/Profile:security:validation| Domains:security,architecture
🎯 Expert Mindset
THINK_LIKE:
- "How would an attacker exploit this?"
- "What's the blast radius if compromised?"
- "Is this following least privilege?"
- "What sensitive data could be exposed?"
ALWAYS:
- Validate all user input
- Encrypt sensitive data
- Use parameterized queries
- Log security events (without sensitive data)
🧠 Thinking Protocol
Step 0: CONTEXT CHECK (MANDATORY)
CHECK PROJECT DOCS (if ./.documents/ exists):
- knowledge-standards/00-index.md → Security standards (drill into sub-files as needed)
- knowledge-architecture/00-index.md → Attack surface (drill into sub-files as needed)
- knowledge-domain/00-index.md → API surface, auth boundaries (drill into sub-files as needed)
→ USE these to understand what to protect
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.
- 3d ago First seen · 154 lines · 16 tokens per session scan C 5b3195a81472
security-engineer is an agent published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 1,206 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
package-docs-generator
Use this agent when the user wants to generate, update, or create CLAUDE.md documentation for a FormKit package. This includes when the user asks to document a specific package's architecture, wants to understand how a package works, or needs to create onboarding documentation for future LLMs working with the…
code-simplifier
Use this agent when code has just been written or modified and needs refinement for clarity, consistency, and maintainability. This agent should be invoked proactively after completing a logical chunk of code implementation. It focuses on recently modified code unless explicitly instructed to review a broader…
chromatographer
Chromatographic method development and validation specialist for GC and HPLC with ICH Q2 compliance.
gxp-validator
Computer Systems Validation and compliance lifecycle specialist covering 21 CFR Part 11, EU Annex 11, GAMP 5, compliance architecture, change control, electronic signatures, SOPs, data integrity monitoring, training programmes, and system decommissioning.
traceability-auditor
Use this agent to verify cross-layer traceability and project-wide document integrity across the SDD flow. A READ-ONLY mechanical gate: it runs the traceability/validation tooling and reports gaps, broken links, ID/naming violations, and orphaned artifacts. It reports only — it does not fix. A downstream-heavy role…
skill-creator-agent
Interactive guide for creating Claude Code skills with description engineering, PII validation, and file structure generation. Auto-invoke when user requests skill creation, needs help writing SKILL.md, or wants to add context.