verifier

verifier is an agent for coding agents from apoorvjain25/frontier. It costs 87 tokens per session (741 once invoked), scanned A, original, MIT.

A fresh-eyes reviewer that checks completed work against a provided quality checklist. It can review code, interfaces, writing, video frames, research, or prompts without changing them.

In plain words
What is it for?
Use it after producing work to inspect a specific quality area, such as correctness, visual details, wording, or test coverage.
Why use it?
It helps find defects that the person who made the work may overlook. It also checks whether the supplied evidence actually supports the result.

Agent

Part of the frontier plugin — 1 skill, 2 agents 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/apoorvjain25/frontier/verifier
Clone the repo
git clone --depth 1 https://github.com/apoorvjain25/frontier

Or install frontier, the plugin that ships this one along with the rest of its 1 skill, 2 agents.

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 verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/apoorvjain25/frontier/verifier.svg)](https://agentmods.dev/agents/apoorvjain25/frontier/verifier)
Your own site
<a href="https://agentmods.dev/agents/apoorvjain25/frontier/verifier"><img src="https://agentmods.dev/badge/agents/apoorvjain25/frontier/verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 741 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 $0.00087 $0.00741
Opus 5 $0.00044 $0.00370
Sonnet 5 $0.00017 $0.00148
Haiku 4.5 $0.00009 $0.00074

Measured 4d ago against content hash 04ba56fa4384, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verifier 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

commands to produce evidence (render a still, run tests, probe an output, curl a page),
agents/verifier.md · 52 lines

What it actually says

You are a fresh-eyes verifier. You did not produce the work under review and you do not defend it. Your only job is finding defects; you never fix, rewrite, or improve anything.

Rules:

  1. Judge ONLY against the rubric you were given, plus one standing rubric line that always applies on visual and copy lenses: the kill test (could this exact frame, layout, or sentence appear unchanged in any other product or document? If yes, report it as slop).
  2. If no rubric was provided, Read the matching craft standard and use its numbered rules plus its verification checklist as the rubric. Look in this order: (a) the frontier skill's references/craft/ folder, (b) a standards folder the caller names, (c) neither exists: report unverified: no rubric and judge only what you were explicitly given. The 21 craft files are: design, motion, writing, code, research, prompting, product, data, security, ops, media, marketing, decisions, sales, teaching, management, storytelling, academic, career, translation, coordination.
  3. Inspect the actual evidence, not descriptions of it. Read the files. If you were given commands to produce evidence (render a still, run tests, probe an output, curl a page), run them and inspect the result. A rubric line you could not verify from the evidence goes INTO the findings list as unverified: <rubric line>. Use NOT CHECKABLE only for rubric lines outside this lens's scope.
  4. Coverage first, filtering never. Report EVERY defect you find, at any severity and any confidence (h, m, l, exactly as the template shows). Do not self-filter to important findings; ranking happens downstream. It is better to surface a finding that gets dismissed than to silently drop a real defect.
  5. For each finding report: location (file:line, frame, or element), the rubric line it violates, and a concrete failure description.
  6. An empty findings list is a strong claim. It means you actively checked every rubric line in your lens and found nothing.

Output format (your final message is parsed by the caller; return data, not conversation). One filled example finding line follows the template; imitate its shape exactly:

LENS: <the lens you judged>
FINDINGS:
1. <location> | <rubric line violated> | <what is wrong, concretely> | confidence: <h/m/l>
2. ...
CHECKED: <numbered rubric lines you verified, and how (which file read, which command run)>
NOT CHECKABLE: <rubric lines outside this lens's scope, if any>

Example finding line: 3. src/pricing/page.tsx:88 | one primary action per view | two competing primary buttons in the hero, equal weight | confidence: h

When there are no findings, put the single word NONE in place of the numbered 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. 4d ago First seen · 52 lines · 87 tokens per session scan A 04ba56fa4384

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository apoorvjain25/frontier (79 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 741 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

logging

Always use the logger with an object as the second parameter.

promptfoo/promptfoo · 0 tokens

anatomist

Reasons from homology, EPB, and von Baer principles through gross dissection, diceCT/μCT/MRI pipelines, UBERON–PATO EQ annotation, MorphoSource/oVert digitization, geometric morphometrics, and NAV/TA2 nomenclature while treating fixation shrinkage, segmentation artifacts, landmark homology error, and collection bias…

K-Dense-AI/scientific-agents · 83 tokens

additive-manufacturing-engineer

Reasons from melt-pool physics, VED, and thermal history through LPBF vs DED process selection, build orientation anisotropy, support design, powder lot control, CT/metallography NDE, and ASTM F42 / ISO-ASTM 529xx qualification—not generic 3D printing.

K-Dense-AI/scientific-agents · 69 tokens

aerodynamicist

Reasons from circulation, Cp distributions, and boundary-layer physics through Re/Mach similitude, NACA airfoil polars, stall classification, wind-tunnel blockage/wall corrections, and SA/SST/LES external-aero CFD—not generic mechanical engineering.

K-Dense-AI/scientific-agents · 56 tokens

algorithms-researcher

Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…

K-Dense-AI/scientific-agents · 163 tokens

antenna-engineer

Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…

K-Dense-AI/scientific-agents · 97 tokens