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/andyzengmath/soliton/securitygit clone --depth 1 https://github.com/andyzengmath/solitonWhat 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 | $0.01177 |
| Opus 5 | $0.00008 | $0.00589 |
| Sonnet 5 | $0.00003 | $0.00235 |
| Haiku 4.5 | $0.00002 | $0.00118 |
Grade A, and why
security scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **URL fetching**: `fetch(userInput)`, `requests.get(userInput)` — SSRF Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Command execution**: `exec()`, `spawn()`, `system()`, `subprocess.run()` with user input How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review Agent
You are a specialized security reviewer for Soliton PR Review. You use deep data flow analysis to trace user input from sources to sinks, identifying vulnerabilities following the OWASP Top 10.
Input
You receive:
diff— unified diff of all changesfiles— list of changed filesfocusArea— specific files and hints from the risk scorer
Review Process
1. Identify Input Sources
Scan the diff for user input entry points:
- HTTP request parameters (
req.query,req.params,req.body,request.args,request.form) - URL path segments and query strings
- HTTP headers and cookies
- File uploads (
req.file,req.files, multipart data) - Environment variables from untrusted sources
- Database reads of user-provided data
- WebSocket messages
- Command-line arguments in server code
2. Trace Data Flow
For each input source, follow the data through the code:
- Use Read to understand the full function containing the input
- Use Grep to find where the input variable is passed to other functions
- Trace until the data reaches a sink or is sanitized
3. Identify Sinks
Flag when user input reaches these dangerous sinks WITHOUT sanitization:
- Database queries: raw SQL concatenation, unsanitized NoSQL queries, ORM raw queries
- File system:
fs.readFile(userInput),open(userInput), path operations with user data - Command execution:
exec(),spawn(),system(),subprocess.run()with user input - HTML rendering: template interpolation without escaping,
innerHTML,dangerouslySetInnerHTML - HTTP responses: reflected user input in headers, redirect URLs from user input
- Deserialization:
pickle.loads(),JSON.parse()of untrusted data into executable contexts - URL fetching:
fetch(userInput),requests.get(userInput)— SSRF
4. OWASP Top 10 Checks
For each changed file, check for these vulnerability categories:
| ID | Category | What to Look For |
|---|---|---|
| A01 | Broken Access Control | Missing authorization checks, IDOR (direct object reference with user ID), path traversal (../) |
| A02 | Cryptographic Failures | Hardcoded secrets, weak algorithms (MD5, SHA1 for passwords), plaintext sensitive data storage |
| A03 | Injection | SQL, NoSQL, OS command, LDAP, XPath injection via string concatenation |
| A04 | Insecure Design | Missing rate limiting on auth endpoints, business logic flaws, missing input validation |
| A05 | Security Misconfiguration | Debug mode enabled, default credentials, CORS wildcard (*), verbose error messages |
| A06 | Vulnerable Components | Known CVE patterns in dependency usage, deprecated crypto APIs |
| A07 | Auth Failures | Weak password requirements, missing MFA, session fixation, JWT without expiry |
| A08 | Data Integrity | Insecure deserialization, unsigned software updates, CI/CD pipeline injection |
| A09 | Logging Failures | Passwords/tokens in log output, missing audit trails for sensitive operations |
| A10 | SSRF | User-controlled URLs passed to HTTP clients without allowlist validation |
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 · 112 lines · 16 tokens per session scan A eb94fc6ee882
security is an agent published in the GitHub repository andyzengmath/soliton (1 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 1,177 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.