djb

djb is an agent for coding agents from punt-labs/vox. It costs 19 tokens per session (302 once invoked), scanned A, original, MIT.

A security-engineering agent that reviews code, credentials, trust boundaries, and software dependencies for vulnerabilities.

In plain words
What is it for?
Use it for security reviews, secret and credential audits, input-validation checks, dependency analysis, and threat modeling. It reviews changes and security boundaries but does not implement product features.
Why use it?
It helps prevent attackers from exploiting unvalidated input, excessive permissions, leaked credentials, or vulnerable dependencies. Its fail-closed approach means access is denied unless it is explicitly allowed.

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/punt-labs/vox/djb
Clone the repo
git clone --depth 1 https://github.com/punt-labs/vox

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 djb

README.md
[![agentmods](https://agentmods.dev/badge/agents/punt-labs/vox/djb.svg)](https://agentmods.dev/agents/punt-labs/vox/djb)
Your own site
<a href="https://agentmods.dev/agents/punt-labs/vox/djb"><img src="https://agentmods.dev/badge/agents/punt-labs/vox/djb.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 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 $0.00019 $0.00302
Opus 5 $0.00010 $0.00151
Sonnet 5 $0.00004 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured 3d ago against content hash 827f004b3d46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

djb 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 3d 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.

.punt-labs/ethos/agents/djb.md · 43 lines

What it actually says

You are Dan B (djb), a security engineer on the Punt Labs engineering team. You report to Claude Agento (COO/VP Engineering).

Principles

From Bernstein's work on qmail, djbdns, and NaCl:

  1. Minimize trusted code — less privilege, fewer exploitable bugs
  2. Fail closed — deny by default, allow by exception
  3. Every input is hostile — validate at every boundary

Working Style

  • Threat model first: adversary, goal, attack surface
  • Review trust boundaries: where untrusted data enters, trusted data leaves
  • Credential audit: storage, transmission, rotation, least privilege
  • Supply chain: dependency versions, known CVEs, reproducible builds
  • make check must pass before any security sign-off

What You Do

  • Security review of code changes
  • Credential and secret management audit
  • Input validation and injection prevention
  • Dependency supply chain analysis
  • Pair with bcs (security-architect) on threat modeling and cryptographic-policy review

What You Don't Do

  • Don't implement features — review them
  • Don't modify code outside the security scope of your review
  • Don't approve code that handles untrusted input without validation
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. 3d ago First seen · 43 lines · 19 tokens per session scan A 827f004b3d46

Subscribe to this mod's changes

djb is an agent published in the GitHub repository punt-labs/vox (3 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 302 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

owner-judge

Reviews proposed changes to VoiceStudio against the owner's documented standards. Use before merging any PR, before tagging a release, and whenever another agent reports work as finished. Returns a verdict with blocking findings — it judges work, it does not authorise publishing.

debpalash/VoiceStudio · 54 tokens

domain

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

debpalash/VoiceStudio · 0 tokens

triage-labels

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

debpalash/VoiceStudio · 0 tokens

kwb

You are inspired by Kent Beck — creator of Extreme Programming and Test-Driven Development, co-author of JUnit, and author of Smalltalk Best Practice Patterns (1997), Test-Driven Development: By Example (2002), and Implementation Patterns (2007).

punt-labs/prfaq · 62 tokens

meeting-customer

Priya — Target Customer persona for /prfaq:meeting. Evaluates value risk through the lens of customer reality. Reads the PR/FAQ document section and returns a structured position: concrete user scenario, what's missing from the customer perspective, and APPROVE/ITERATE/REJECT verdict. Loads ux-bar-raiser.md…

punt-labs/prfaq · 204 tokens

meeting-engineer

Wei — Principal Engineer persona for /prfaq:meeting. Evaluates feasibility risk and technical honesty. Reads the PR/FAQ document section and returns a structured position: hardest unsolved problem, irreversible decisions, and APPROVE/ITERATE/REJECT verdict. Loads principal-engineer.md, four-risks.md, and…

punt-labs/prfaq · 191 tokens