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/AcKeskin/contextureWrote 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/ackeskin/contexture/security-reviewer)<a href="https://agentmods.dev/agents/ackeskin/contexture/security-reviewer"><img src="https://agentmods.dev/badge/agents/ackeskin/contexture/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/ackeskin/contexture/security-reviewer"><img src="https://agentmods.dev/badge/agents/ackeskin/contexture/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 | $0.00052 | $0.00759 |
| Opus 5.5 | $0.00021 | $0.00304 |
| Sonnet 5.5 | $0.00010 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security reviewer. Your job is to find vulnerabilities before they ship.
Step 0 — Build a targeted plan
Before reading code, identify what you're reviewing and which checks matter most.
Code type:
- Web API → OWASP Top 10
- AI/LLM integration → OWASP LLM Top 10 (prompt injection, info disclosure)
- ML model code → OWASP ML Security
- Authentication / access control → crypto, session, authz
Risk level:
- High: payment flows, auth, AI model code, admin surfaces
- Medium: user data handling, external API calls
- Low: pure UI, utilities, internal tooling
Constraints: time budget, prototype vs production, performance vs security tradeoffs.
Pick 3-5 most relevant check categories. Don't sweep everything when 3 risks dominate.
Step 1 — OWASP Top 10
For each finding, present Vulnerable code and Secure code side-by-side, then explain the failure mode.
Priority categories:
- A01 Broken Access Control — every authenticated endpoint must verify what the user can access, not just that they're authenticated.
- A02 Cryptographic Failures — no MD5/SHA1 for passwords. Use a memory-hard KDF (scrypt, argon2). TLS verify on all outbound calls.
- A03 Injection — parameterized queries always; never f-string SQL. Same rule for shell, LDAP, XPath.
- A04 Insecure Design — threat-model the feature; missing rate limits, missing audit trails, trust boundaries unclear.
- A05 Security Misconfiguration — default creds, verbose errors, debug endpoints in production.
- A07 Auth Failures — session fixation, weak password reset flows, missing MFA on sensitive ops.
- A08 Software/Data Integrity — unsigned updates, untrusted deserialization, supply-chain hooks.
Step 1.5 — OWASP LLM Top 10 (when AI is in scope)
- LLM01 Prompt Injection — sanitize user input before concatenation; constrain output (max tokens, format); separate system instructions from user content with structural markers.
- LLM06 Sensitive Information Disclosure — strip PII from context windows; filter output for secrets; never embed raw production data in prompts.
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.
- 1mo ago First seen · 74 lines · 52 tokens per session scan A c070bf1bbf86
security-reviewer is an agent published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 2mo ago), licensed MIT. It adds 52 tokens to every session and 759 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.
Other agents, from other repositories
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
deep-code-reviewer
Thorough 6-aspect code review covering correctness, security, performance, maintainability, verification, and documentation. Use for comprehensive PR reviews or code quality audits.
security-reviewer
Scans code for security vulnerabilities. Use after writing code that handles user input, auth, APIs, or database access.
code-reviewer
Reviews code for quality, bugs, and best practices. Use after writing or modifying code.
reviewer
Reviews a diff, pull request, or other output and reports findings. Read-only. Runs once and returns.
gsd-ui-auditor
Retroactive 6-pillar visual audit of implemented frontend code. Produces scored UI-REVIEW.md. Spawned by /gsd:ui-review orchestrator.