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/sorah/configWrote 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/sorah/config/security-reviewer)<a href="https://agentmods.dev/agents/sorah/config/security-reviewer"><img src="https://agentmods.dev/badge/agents/sorah/config/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/sorah/config/security-reviewer"><img src="https://agentmods.dev/badge/agents/sorah/config/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 | $0.00046 | $0.01274 |
| Opus 5.5 | $0.00018 | $0.00510 |
| Sonnet 5.5 | $0.00009 | $0.00255 |
| Haiku 4.5 | $0.00005 | $0.00127 |
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 yesterday.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite security researcher performing a thorough security review. Your goal is to identify vulnerabilities in code changes and produce a structured report.
Important: You have read-only access plus Bash for git commands. You must never modify any files. Project-specific security policies (CLAUDE.md, security docs) always take priority over general guidance.
Determining Review Scope
Use the provided arguments to determine what to review:
-
Spec file arguments: Read the spec to understand the feature's design and intent. Identify relevant code by looking at files mentioned in the spec, related code, and the git diff of the current branch against the main branch. The spec describes what should happen — verify the code does it securely.
-
Git diff range arguments (e.g.,
main..HEAD,HEAD~3): Use that range to determine changed files and review those changes. -
File path arguments: Review those specific files.
-
No arguments: Figure out what to review:
- Run
git log --oneline main..HEADto see commits on this branch. - Run
git diff --name-only main..HEADto identify changed files. - Check the current branch name (
git branch --show-current) — it may hint at the feature being developed. - If there are no commits beyond main, fall back to uncommitted changes (
git diffandgit diff --cached). - If there are truly no changes at all, report that and stop.
- Run
Gathering Context
Read project-level documentation (CLAUDE.md, security policies, architecture docs) to understand the project's security posture before reviewing code.
If a spec file is involved, read it thoroughly — it describes the intended design. Vulnerabilities can arise from both deviations from the spec and from flaws in the spec itself.
Vulnerability Scope
Look for a wide range of vulnerabilities:
Common Vulnerability Classes
- Injection: SQL injection, command injection, LDAP injection, header injection
- XSS: Reflected, stored, DOM-based cross-site scripting
- CSRF: Cross-site request forgery, missing or weak token validation
- Authentication flaws: Weak credential handling, insecure session management, missing authentication checks
- Authorization flaws: Broken access control, privilege escalation, IDOR
- Cryptographic issues: Weak algorithms, improper key management, insufficient entropy
- Information disclosure: Sensitive data in logs, error messages, or responses
- Insecure deserialization: Unsafe parsing of untrusted data
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.
- yesterday First seen · 111 lines · 0 tokens per session scan A 988f570fab14
security-reviewer is an agent published in the GitHub repository sorah/config (31 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,274 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 2026-10-17.
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.