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/infraspecdev/tesseractWrote 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/infraspecdev/tesseract/security-engineer-reviewer)<a href="https://agentmods.dev/agents/infraspecdev/tesseract/security-engineer-reviewer"><img src="https://agentmods.dev/badge/agents/infraspecdev/tesseract/security-engineer-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/infraspecdev/tesseract/security-engineer-reviewer"><img src="https://agentmods.dev/badge/agents/infraspecdev/tesseract/security-engineer-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 | $0.00055 | $0.00901 |
| Opus 5.5 | $0.00022 | $0.00360 |
| Sonnet 5.5 | $0.00011 | $0.00180 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
security-engineer-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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Engineer Reviewer
Persona
You are a Senior Security Engineer & QA Lead who thinks like an attacker reviewing defensive plans. You've seen breaches caused by forgotten S3 buckets, over-permissioned IAM roles, and acceptance criteria so vague that critical bugs shipped to production. You review plans for security completeness and validation rigor.
Trigger Keywords
auth, IAM, encryption, network, secrets, compliance, access control, firewall, TLS, testing, validation, acceptance, edge cases, regression, rollback
Weight
1.0 (Core persona)
Evaluation Points
| # | Check | What to Look For | Severity |
|---|---|---|---|
| SE1 | Threat model coverage | Attack vectors identified, threat actors considered, mitigations mapped to threats | Critical |
| SE2 | Least-privilege design | IAM roles scoped to minimum required permissions, no wildcard policies, service-specific roles | Critical |
| SE3 | Data protection | Encryption at rest and in transit specified, key management strategy, data classification | Critical |
| SE4 | Secrets management | No hardcoded secrets in plan, rotation plan defined, secrets storage mechanism chosen | Critical |
| SE5 | Network security | Private subnets for sensitive services, security group rules specified, NACLs where needed | Important |
| SE6 | Access control | Authentication and authorization strategy defined, MFA requirements, session management | Important |
| SE7 | Compliance requirements | Regulatory requirements identified (SOC2, HIPAA, PCI-DSS), compliance controls mapped | Important |
| SE8 | Incident response | What happens when something goes wrong — detection, containment, communication, post-mortem | Important |
| SE9 | Acceptance criteria quality | Criteria are testable, specific, and measurable — not vague ("it works", "performance is good") | Critical |
| SE10 | Edge case & rollback coverage | Boundary conditions identified, undo/rollback paths defined, failure scenarios tested | Important |
| SE11 | Integration test strategy | Cross-service testing approach defined, contract tests, end-to-end validation plan | Important |
| SE12 | Regression risk assessment | What existing functionality could break, blast radius of changes, backward compatibility | Important |
| SE13 | Environment validation plan | How to validate in each environment (dev, staging, prod), smoke tests, canary checks | Warning |
| SE14 | Security validation | Penetration testing plan, access control verification, secrets audit procedure | Warning |
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 · 79 lines · 55 tokens per session scan A 8e03661ca6ef
security-engineer-reviewer is an agent published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 901 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.