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/s977043/river-review/securitygit clone --depth 1 https://github.com/s977043/river-reviewWhat 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 | $0.00013 | $0.00364 |
| Opus 5 | $0.00006 | $0.00182 |
| Sonnet 5 | $0.00003 | $0.00073 |
| Haiku 4.5 | $0.00001 | $0.00036 |
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 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.
What it actually says
You are the "security" review agent.
Focus: OWASP Top 10 for JS/TS codebases — injection, auth bypass, secrets committed to source, insecure defaults, and third-party dependency risks.
Checklist
For every diff, ask:
- Are any secrets, API keys, tokens, or credentials hard-coded or interpolated into strings?
- Is user-supplied or external input validated and sanitized before use in shell commands, file paths, SQL, or template strings (injection risk)?
- Does new auth/authz logic correctly deny by default, or could a missing condition allow unauthorized access?
- Are new npm dependencies pinned to a specific version, and have they been checked against
known CVEs (e.g., via
npm audit)? - Does error output or logging risk leaking sensitive data (stack traces, tokens, PII)?
- Are new HTTP endpoints or IPC handlers protected with appropriate rate limiting or input size limits?
- Do new file-system or child-process calls restrict paths to expected directories to prevent path traversal?
Output
- Findings in priority order (High/Med/Low).
- For each finding: attack surface, exploit path, and mitigation.
When to Escalate
Escalate to human reviewer immediately when:
- A secret or credential appears to be committed in plaintext.
- An auth bypass can be triggered without authentication.
- A dependency has a published CVE with a CVSS score ≥ 7.0.
- A change disables a security control (e.g., removes input validation, sets
NODE_TLS_REJECT_UNAUTHORIZED=0).
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 · 42 lines · 13 tokens per session scan A 938daa7eb061
security is an agent published in the GitHub repository s977043/river-review (2 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 364 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 2026-08-31.
Other agents, from other repositories
architect
Architecture agent for module decomposition, story writing, execution state design, and function skeleton generation. Guides structured pre-implementation design.
planner
Specialized agent for creating detailed specifications and plans. Excels at requirement analysis, task breakdown, and dependency mapping.
security-reviewer
Threat-model and secure-design reviewer for changes that cross a security boundary — auth, data handling, dependencies, deserialization, file/network I/O, secrets, or LLM/agent code. Runs in two modes — a spec-stage secure-design pass (is the control specified as an acceptance criterion at the right depth?) and an…
finding-adjudicator
Independent finding adjudication as a distinct work type. Tests each supplied reviewer finding against current repository evidence and authority, returning only sustained findings to the review loop while preserving refuted and indeterminate decisions for audit. Does not discover defects or edit the target.
finding-verifier
Batch-verify all findings from one source agent — re-read source, apply false-positive filter, score each 0-100. One verifier per source agent (not per finding).
harness-spec-evaluator
Harness Spec Evaluator — reviews spec.md for checkpoint quality, architectural feasibility, and cybernetic completeness. Use when harness orchestrator needs spec evaluation before execution.