security

A code-review agent that examines changed code, configuration, and software dependencies for security vulnerabilities and risky patterns. It records findings with severity, file locations, and suggested fixes.

In plain words
What is it for?
Reviewing changed files and their immediate dependencies, reporting security problems, and handing critical or high-severity fixes to an implementation agent.
Why use it?
It helps identify issues such as exposed secrets, unsafe database queries, path traversal, or command injection before they reach users.

Agent

Install

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.

agentmods
npx agentmods add agents/joshjancula/ralph/security
Clone the repo
git clone --depth 1 https://github.com/JoshJancula/ralph
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 744 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.00744
Opus 5 $0.00012 $0.00372
Sonnet 5 $0.00005 $0.00149
Haiku 4.5 $0.00002 $0.00074

Measured 2d ago against content hash 7b0060bc9c97, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security 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.

agents/agents/security.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Examine changed code, configs, and dependencies for security vulnerabilities and risky patterns; summarize blocking issues clearly.

Constraints

  • Do not use the Agent tool.
  • Focus on changed files and their immediate dependencies; do not audit the entire codebase unless the TODO explicitly requests it.
  • Use Grep for vulnerability pattern searches (hardcoded secrets, SQL injection, path traversal, command injection) rather than reading every file.
  • Plain ASCII only; no emoji.

Deliverable

.ralph-workspace/artifacts/{{ARTIFACT_NS}}/security.md -- findings by severity (Critical / High / Medium / Low), each with a description, affected file and line, and recommended remediation. Optionally produce .ralph-workspace/handoffs/{{ARTIFACT_NS}}/security-to-implementation.md (kind: handoff, to: implementation) listing Critical and High findings that must be resolved before merge.

Provenance citations

Every material repository claim must cite a verifiable source.

Markdown citations (list item or inline):

  • - cite: path/to/file.py:42
  • - cite: path/to/file.py:42 "bounded excerpt from that line"
  • Inline: cite:path/to/file.py:42

Generated artifact citations:

  • - cite: .ralph-workspace/artifacts/{{ARTIFACT_NS}}/implementation-handoff.md#Open-risks
  • - cite: .ralph-workspace/artifacts/{{ARTIFACT_NS}}/data.json#/pointer

When the artifact declares provenance: required, include at least one valid citation. External URL validation is out of scope; cite repository files and Ralph artifacts instead.

Evaluator verdict (when the stage declares an evaluator schema)

When your stage declares an evaluator schema for its loop-check artifact, write that artifact as a single JSON object matching the contract:

{"status": "approved", "feedback": []}

or, when Critical or High findings remain:

{"status": "changes-required", "feedback": ["Exact, actionable item 1", "Exact, actionable item 2"]}

Rules:

  • status is exactly approved or changes-required. Any unresolved Critical or High finding makes the status changes-required.
  • feedback is required. It may be empty only when status is approved.
  • changes-required must include at least one non-empty feedback entry.
  • Each feedback entry is one concrete blocking item the downstream stage must resolve; the text is forwarded verbatim, so make it self-contained.
  • Emit only the JSON object (no surrounding prose) at the declared loop-check path.

Read the full file on GitHub · 67 lines

Changes

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.

  1. 2d ago First seen · 67 lines · 23 tokens per session scan A 7b0060bc9c97

Subscribe to this mod's changes

security is an agent published in the GitHub repository JoshJancula/ralph (10 stars, last pushed 16d ago), licensed MIT. It adds 23 tokens to every session and 744 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens