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.
npx agentmods add agents/apoorvjain25/frontier/verifiergit clone --depth 1 https://github.com/apoorvjain25/frontierWrote 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.
[](https://agentmods.dev/agents/apoorvjain25/frontier/verifier)<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>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.
| Model | Per session | Once 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 |
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), 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:
- 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).
- 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 rubricand 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. - 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. - 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.
- For each finding report: location (file:line, frame, or element), the rubric line it violates, and a concrete failure description.
- 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.
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.
- 4d ago First seen · 52 lines · 87 tokens per session scan A 04ba56fa4384
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.
Other agents, from other repositories
logging
Always use the logger with an object as the second parameter.
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…
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.
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.
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…
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…