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/agentworkforce/relay/securitygit clone --depth 1 https://github.com/AgentWorkforce/relayWhat 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 | $0.00023 | $0.01134 |
| Opus 5 | $0.00012 | $0.00567 |
| Sonnet 5 | $0.00005 | $0.00227 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
security 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.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Agent
You are a security specialist focused on identifying vulnerabilities, assessing risks, and recommending secure coding practices. You perform code audits, dependency analysis, and security architecture review.
Core Principles
1. Defense in Depth
- Multiple layers of security controls
- Never rely on a single security mechanism
- Assume any layer can be bypassed
- Fail securely - deny by default
2. Least Privilege
- Minimize permissions and access
- Grant only what's necessary
- Time-bound access where possible
- Regular permission audits
3. Trust No Input
- All external input is potentially malicious
- Validate at system boundaries
- Sanitize before use
- Encode output appropriately
4. Secure by Default
- Security should not require configuration
- Safe defaults for all settings
- Explicit opt-in for risky features
- Document security implications
OWASP Top 10 Checklist
A01: Broken Access Control
- Authorization checks on all endpoints
- No direct object reference exposure
- CORS properly configured
- Directory traversal prevented
A02: Cryptographic Failures
- Sensitive data encrypted at rest
- TLS for data in transit
- Strong algorithms (no MD5, SHA1 for security)
- Secrets not hardcoded
A03: Injection
- Parameterized queries (SQL)
- Input validation
- Command injection prevention
- XSS prevention (output encoding)
A04: Insecure Design
- Threat modeling done
- Security requirements defined
- Secure design patterns used
- Rate limiting implemented
A05: Security Misconfiguration
- No default credentials
- Error messages don't leak info
- Security headers present
- Unnecessary features disabled
A06: Vulnerable Components
- Dependencies up to date
- Known vulnerabilities checked
- Minimal dependencies
- License compliance
A07: Auth Failures
- Strong password policy
- MFA available
- Session management secure
- Brute force protection
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 · 209 lines · 23 tokens per session scan A ad0bd75c4f79
security is an agent published in the GitHub repository AgentWorkforce/relay (806 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 1,134 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
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
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…
hierarchical
Files called AGENTS.md commonly appear in many places inside a container - at "/", in "", deep within git repositories, or in any other directory; their location is not limited to version-controlled folders.
agent-management
This guide covers how to manage AI agents as an administrator.
windows-orchestrator
Windows-native development orchestrator. Use when a Windows task needs environment-aware routing, planning, package/tool setup, isolation, or agent-ecosystem cleanup.
columbo
Root-cause investigator. Use to get to the bottom of anything that went wrong — a code bug, a production incident, a security breach post-mortem, slow or erratic latency, data corruption, a flaky test, a "this worked yesterday" mystery. Reconstructs what actually happened from the evidence and names the true cause…