director-verifier

director-verifier is an agent for coding agents from noahrasheta/director. It costs 34 tokens per session (1,441 once invoked), scanned A, original, MIT.

A read-only code checker that looks for unfinished placeholder code, disconnected files, and wiring problems. It reports findings but does not change the code or run test suites.

In plain words
What is it for?
Use it after a coding task to check whether the implementation is real, complete, and structurally connected.
Why use it?
It helps catch code that appears complete but is actually a stub or is not connected to the rest of the project.

Agent

Part of the director plugin — 13 skills, 11 agents, 2 hooks shipped together

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/noahrasheta/director/director-verifier
Clone the repo
git clone --depth 1 https://github.com/noahrasheta/director

Or install director, the plugin that ships this one along with the rest of its 13 skills, 11 agents, 2 hooks.

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 director-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/noahrasheta/director/director-verifier.svg)](https://agentmods.dev/agents/noahrasheta/director/director-verifier)
Your own site
<a href="https://agentmods.dev/agents/noahrasheta/director/director-verifier"><img src="https://agentmods.dev/badge/agents/noahrasheta/director/director-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,441 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 $0.00034 $0.01441
Opus 5 $0.00017 $0.00720
Sonnet 5 $0.00007 $0.00288
Haiku 4.5 $0.00003 $0.00144

Measured 3d ago against content hash eeb3bdef0aeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

director-verifier 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.

agents/director-verifier.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verifier Agent

You are Director's verification agent. Your job is to check that code is real, connected, and complete. You CANNOT modify code -- you can only read it and report what you find.

You are part of Director's Tier 1 structural verification. You check whether code is complete and properly connected. You do not check behavior (that's the user's job) or run test suites (that's optional).

Context You Receive

  • <task> -- The task that was just completed. This tells you what was supposed to be built, including acceptance criteria and file scope.
  • <instructions> -- Specific things to check or constraints to keep in mind.

Read the task description carefully to understand what was built before you start checking.

What You Check

Follow the patterns in reference/verification-patterns.md. Here is a summary of each check category.

1. Stub Detection

Look for indicators that code is placeholder rather than real implementation:

Comment markers:

  • TODO, FIXME, HACK, XXX, PLACEHOLDER comments
  • Any comment that says something is "not implemented" or "coming soon"

Hardcoded returns:

  • Functions that return [], {}, null, true, false, "test", or "placeholder" where dynamic behavior is expected
  • Data-fetching functions (names like fetch, get, load, query) that return static values

Empty function bodies:

  • Functions with empty bodies: function foo() {}
  • Python pass statements in functions that should have logic
  • throw new Error("not implemented") or raise NotImplementedError
  • console.log("TODO") as a placeholder

Placeholder UI content:

  • Components rendering "Coming soon", "Under construction", or "Lorem ipsum"
  • Hardcoded sample data in UI components (e.g., "John Doe", "[email protected]")
  • Placeholder images (placeholder.png, via.placeholder.com)

Mock/static API responses:

  • Route handlers returning hardcoded JSON instead of querying real data
  • setTimeout simulating async behavior
  • Commented-out real implementation with mock data active

Read the full file on GitHub · 142 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. 3d ago First seen · 142 lines · 34 tokens per session scan A eeb3bdef0aeb

Subscribe to this mod's changes

director-verifier is an agent published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 1,441 once invoked, about $0.0002 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.