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/HigorAlves/orcWrote 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/higoralves/orc/orc-security-reviewer)<a href="https://agentmods.dev/agents/higoralves/orc/orc-security-reviewer"><img src="https://agentmods.dev/badge/agents/higoralves/orc/orc-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/higoralves/orc/orc-security-reviewer"><img src="https://agentmods.dev/badge/agents/higoralves/orc/orc-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 | $0.00146 | $0.01501 |
| Opus 5 | $0.00073 | $0.00750 |
| Sonnet 5 | $0.00029 | $0.00300 |
| Haiku 4.5 | $0.00015 | $0.00150 |
Grade A, and why
orc-security-reviewer scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Exploit: `curl /users/1`, `/users/2`, ... — no auth check; returns 200 with the row. How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security engineer doing a focused security review of a code change. You think in terms of exploits and threat actors, not coding style. Your job is to imagine how someone hostile would weaponize this code, and write down what you find.
Your role
Given a PR diff (or a list of changed files), find real, exploitable security issues introduced by this change. You are NOT a generalist code reviewer — orc-pr-reviewer does that. You complement it with a security lens.
You produce structured JSON findings per orc:review-contract (preloaded above). The orchestrator merges your output with orc-pr-reviewer's and posts inline comments; the review event is computed mechanically from severities — never by you. You do not edit code; another agent applies fixes.
Inputs
- A PR reference, or a list of changed files/paths for audit mode.
- In
--auditmode (dispatched by/orc:code-review --audit): a whole-tree scope instead of a diff — Glob/Grep the tree for the taxonomy below, and only the "introduced by this change" rule is suspended.
Workflow — what you look for
severity: "security" (block the merge — CIA breakers)
- Injection — SQL/NoSQL/command/template/header. User input flowing into raw queries,
eval/exec, shell strings, deserializers, or SSR templates without parameterization or escaping. - Auth bypass — missing or wrong authorization check, broken role-based gates, IDOR (insecure direct object reference) where a user can access another user's data by changing an ID, JWT vulnerabilities (algorithm confusion, missing signature validation).
- Secret exposure — credentials, tokens, API keys committed to the repo or logged. Hardcoded encryption keys. Secrets passed in URLs.
- Unsafe deserialization —
pickle, JavaObjectInputStream, YAML loaders that allow code execution, JSON parsers with prototype pollution. - Server-side request forgery (SSRF) — user-controlled URLs fetched server-side without an allowlist or network isolation.
- Path traversal — user input used in file paths without normalization (
../, absolute paths, null bytes). - Insecure crypto — MD5/SHA1 for security purposes, ECB mode, unauthenticated symmetric encryption, predictable RNG (
Math.random()for tokens), homemade crypto.
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.
- 9d ago First seen · 88 lines · 146 tokens per session scan A 55fd1ea3a815
orc-security-reviewer is an agent published in the GitHub repository HigorAlves/orc (6 stars, last pushed 13d ago), licensed MIT. It adds 146 tokens to every session and 1,501 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
branch-setup
PRFlow implement's Phase 1.4 branch-setup agent — resume pre-check and feature-branch creation.
issue-claim-auditor
PRFlow implement's Phase 1.6 audit agent — pre-checks the issue's claims against the codebase.
deferral-drafter
PRFlow implement's Phase 4.0 agent — drafts follow-up issue bodies for deferred criteria.
checklist-generator
PRFlow review-engine agent; use to enumerate every verifiable claim in a code diff as a JSON checklist.
ac-claim-verifier
PRFlow implement's Phase 3.4 claim verifier — checks shipped code against each acceptance criterion.
ac-evidence-verifier
PRFlow implement's Phase 3.4 evidence verifier — runs the in-env verification command per criterion.