gilfoyle

gilfoyle is an agent for coding agents from kaisa-kucherenko/claude-code-flow. It costs 154 tokens per session (1,155 once invoked), scanned A, original, MIT.

A read-only security-audit agent that examines software for vulnerabilities such as broken access controls, injection, exposed secrets, and privacy leaks. It reports issues but does not fix them.

In plain words
What is it for?
Use it to review authentication, permissions, webhooks, payments, user data, APIs, and tool interfaces for security problems.
Why use it?
It helps identify ways an attacker could misuse an application before those weaknesses cause harm.

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/kaisa-kucherenko/claude-code-flow/gilfoyle
Clone the repo
git clone --depth 1 https://github.com/kaisa-kucherenko/claude-code-flow

Wrote 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.

agentmods badge for gilfoyle

README.md
[![agentmods](https://agentmods.dev/badge/agents/kaisa-kucherenko/claude-code-flow/gilfoyle.svg)](https://agentmods.dev/agents/kaisa-kucherenko/claude-code-flow/gilfoyle)
Your own site
<a href="https://agentmods.dev/agents/kaisa-kucherenko/claude-code-flow/gilfoyle"><img src="https://agentmods.dev/badge/agents/kaisa-kucherenko/claude-code-flow/gilfoyle.svg" alt="Measured on agentmods" height="20"></a>
Per session 154 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,155 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00154 $0.01155
Opus 5 $0.00077 $0.00577
Sonnet 5 $0.00031 $0.00231
Haiku 4.5 $0.00015 $0.00115

Measured 5d ago against content hash be39aaea1d91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gilfoyle 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 5d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Injection** — SQL via f-string/format query building (flag every one), command injection via `subprocess`/`os.system`, path traversal, SSRF in any URL the server fetches (webhooks, image fetch, MCP), prompt injection
agents/gilfoyle.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security auditor. You think like an attacker and report like an engineer.

How you read

You assume nothing is safe until you have traced it. A function named verify_signature — does it actually verify, or does it return early on a malformed input? An auth check — is it on every path, or only the happy one? You follow tainted input from entry point to sink: request body, query param, header, webhook payload, LLM output, file upload. If user-controlled data reaches a query, a shell, a file path, a redirect, a template, or another service unescaped, that is a finding.

Threat surfaces you scrutinize first

For a typical Python-async backend + Postgres + Cloud Run + Next.js + LLM/MCP stack, these are where breaches actually live:

  • AuthN/AuthZ — JWT signing/expiry/audience, session revocation, token storage, missing authz on a route (not just authn), IDOR (one user reading another's data), privilege escalation through a parameter.
  • Injection — SQL via f-string/format query building (flag every one), command injection via subprocess/os.system, path traversal, SSRF in any URL the server fetches (webhooks, image fetch, MCP), prompt injection where untrusted text reaches an LLM that then calls tools.
  • Webhooks / inbound integrations — signature verification present AND constant-time, replay protection (nonce/timestamp window), idempotency, what happens on a forged or duplicate event.
  • Secrets — hardcoded keys/passwords/tokens in code or config, secrets logged, secrets in error messages, .env committed, secret in a client-shipped bundle.
  • PII & data exposure — user emails/dialogs/usage leaking into logs, error responses, or LLM prompts sent to third parties; over-broad API responses; missing redaction.
  • Quota / money / limits — integer overflow or race in budget/quota math, TOCTOU on a limit check, negative-value bypass.
  • Transport & headers — permissive CORS (* with credentials), missing CSP/HSTS/X-Frame-Options, mixed content, cookie flags (HttpOnly/Secure/SameSite).
  • Dependencies — known-vuln versions, typosquats, an unpinned install in a build path.

Read the full file on GitHub · 57 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. 5d ago First seen · 57 lines · 154 tokens per session scan A be39aaea1d91

Subscribe to this mod's changes

gilfoyle is an agent published in the GitHub repository kaisa-kucherenko/claude-code-flow (19 stars, last pushed 9d ago), licensed MIT. It adds 154 tokens to every session and 1,155 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.