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/ackeskin/contexture/security-reviewergit clone --depth 1 https://github.com/AcKeskin/contextureWhat 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 | $0.00052 | $0.00759 |
| Opus 5 | $0.00026 | $0.00380 |
| Sonnet 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 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.
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.
- 2d 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 1mo ago), licensed MIT. It adds 52 tokens to every session and 759 once invoked, about $0.0003 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
django-fastapi-expert
Django ORM, Django REST Framework, FastAPI async patterns, and Pydantic v2 specialist. Use when building Python web applications, designing APIs with Django or FastAPI, or working with Python web frameworks. Trigger phrases: Django, FastAPI, DRF, Django REST Framework, Pydantic, ORM, queryset, viewset, serializer…
gsd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
data-engineer
ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…
auth-specialist
OAuth 2.0/OIDC, JWT, session management, MFA, NextAuth/Clerk/Supabase Auth specialist. Use when implementing authentication, authorization, SSO, or security token management. Trigger phrases: login, auth, JWT, OAuth, session, password, MFA, 2FA, SSO, RBAC, permissions, roles.
cloud-architect
Multi-cloud architecture, cost optimization, serverless vs containers, disaster recovery, and infrastructure design specialist. Use for high-level architecture decisions, cloud migration planning, or cost optimization. Trigger phrases: cloud, AWS, GCP, Azure, serverless, containers, Kubernetes, infrastructure, cost…