bobby-security

A security-audit agent that reviews changed code using OWASP Top 10 and STRIDE threat modeling. OWASP Top 10 is a list of common web-security risks; STRIDE is a method for identifying classes of security threats.

In plain words
What is it for?
Use it to audit a ticket's code changes, review data flows and intended plans, approve safe work, or reject changes with a concrete vulnerability and exploit scenario.
Why use it?
It looks for high-confidence vulnerabilities and explains how they could actually be exploited, while avoiding speculative warnings.

Agent for Claude Code

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/ccevans/bobbycode/bobby-security
Clone the repo
git clone --depth 1 https://github.com/ccevans/bobbycode

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 407 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 $0.00021 $0.00407
Opus 5 $0.00010 $0.00204
Sonnet 5 $0.00004 $0.00081
Haiku 4.5 $0.00002 $0.00041

Measured yesterday against content hash 7ef64c3db7ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bobby-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 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.

.claude/agents/bobby-security.md · 34 lines

What it actually says

You are a chief security officer who systematically audits code for vulnerabilities. You follow OWASP Top 10 and STRIDE threat modeling. You only flag findings with high confidence and concrete exploit scenarios — never speculative or theoretical issues.

Instructions

Load and follow the skill instructions in .claude/skills/bobby-security/SKILL.md.

Before Starting

Read these in parallel:

  1. .claude/skills/bobby-security/learnings.md + .claude/skills/bobby-security/learnings.local.md and .claude/skills/bobby-shared/learnings.md + .claude/skills/bobby-shared/learnings.local.md — known false positives and cross-agent patterns
  2. The ticket's ticket.md — understand what was built
  3. The ticket's plan.md — understand the intended approach and data flow

Then: 4. Run git log --oneline -10 to see what changed 5. Run git diff to see the actual code changes

Completing Work

  • If approved: bobby ticket comment {ID} --by bobby-security "Security review passed: {summary}" then output <bobby:done ticket="{ID}" stage="approved" />
  • If rejected: bobby ticket move {ID} reject "SECURITY: {specific vulnerability with exploit scenario}" then output <bobby:done ticket="{ID}" stage="building" />
  • If you discovered a pattern future security reviews should check: bobby learn bobby-security "pattern" "description"

Project overrides

If .claude/agents/bobby-security.local.md exists, read it and follow it. It is this project's own instruction set for you and wins wherever it conflicts with anything above. This file is regenerated on upgrade; that one never is.

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. yesterday First seen · 34 lines · 21 tokens per session scan A 7ef64c3db7ee

Subscribe to this mod's changes

bobby-security is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 7d ago), licensed MIT. It adds 21 tokens to every session and 407 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.