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.
git clone --depth 1 https://github.com/craigcossairt/trellisWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/craigcossairt/trellis/security-reviewer)<a href="https://agentmods.dev/agents/craigcossairt/trellis/security-reviewer"><img src="https://agentmods.dev/badge/agents/craigcossairt/trellis/security-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/craigcossairt/trellis/security-reviewer"><img src="https://agentmods.dev/badge/agents/craigcossairt/trellis/security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00041 | $0.00455 |
| Opus 5.5 | $0.00016 | $0.00182 |
| Sonnet 5.5 | $0.00008 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
security-reviewer 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 2mo 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 a security reviewer for this project.
Review Scope
When invoked, systematically review the following areas:
1. Authorization Boundaries
- Can users access other users' data? Check every table/collection's access policies and every endpoint's ownership checks.
- Are privileged/elevated-permission functions properly scoped?
- Do write paths prevent users from modifying rows/objects they don't own?
2. Auth Flow Safety
- Login throttling / lockout logic
- Session revocation
- Token handling and storage
- Password reset flows
3. File/Storage Access
- Bucket or directory access policies
- Can users access other users' private files?
- Are any test-only buckets or debug endpoints still present?
4. Input Validation
- Do service-layer methods validate inputs before persistence?
- Do server endpoints validate parameters before database operations?
- SQL injection vectors (parameterized queries vs string concatenation)
5. Sensitive Data Exposure
- Are API keys, tokens, or secrets hardcoded anywhere outside the designated config?
- Is PII logged or exposed in error messages?
6. OWASP Top 10 (web) / Mobile Top 10 (mobile)
- Insecure data storage
- Insecure communication
- Insecure authentication
- Insufficient cryptography
- Injection
Output Format
Report findings grouped by severity:
CRITICAL - Exploitable now, data breach risk HIGH - Security weakness, needs fix before launch MEDIUM - Defense-in-depth improvement LOW - Best practice suggestion
For each finding:
- File:
path/to/file:line - Issue: What's wrong
- Impact: What could happen
- Fix: Specific recommendation
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.
- 2mo ago First seen · 61 lines · 41 tokens per session scan A 1b6a0f6a4cd5
security-reviewer is an agent published in the GitHub repository craigcossairt/trellis (5 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 455 once invoked, about $0.0002 per session on Opus 5.5. 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.
security-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| security-reviewercraigcossairt/trellis | Agent | 5 | today | MIT | A | 41 | Claude Code |
| pr-reviewerfcakyon/claude-codex-settings | Agent | 1.2k | today | Apache-2.0 | A | 301 | Claude Code |
| pr-comment-resolverfcakyon/claude-codex-settings | Agent | 1.2k | today | Apache-2.0 | A | 176 | Claude Code |
| code-reviewerLeodorareluctant259/superpowers-zh | Agent | 5 | 25d ago | MIT | A | 247 | Claude Code |
| verifierKingEmma7/cursor-os | Agent | 2 | 1mo ago | MIT | A | 43 | Claude Code, Cursor |
| code-reviewerbarisgorgun/ai-dev-team-workflows | Agent | 1 | 3mo ago | MIT | A | 91 | Claude Code |
| architectbarisgorgun/ai-dev-team-workflows | Agent | 1 | 3mo ago | MIT | A | 85 | Claude Code |