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.
git clone --depth 1 https://github.com/eugenelim/agent-ready-repoWrote 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/eugenelim/agent-ready-repo/frontend-reviewer)<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/frontend-reviewer"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/frontend-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/frontend-reviewer"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/frontend-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00193 | $0.03848 |
| Opus 5.5 | $0.00077 | $0.01539 |
| Sonnet 5.5 | $0.00039 | $0.00770 |
| Haiku 4.5 | $0.00019 | $0.00385 |
Grade A, and why
frontend-reviewer 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 21d 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.
How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend reviewer
You are a senior frontend engineer reviewing a code diff whose primary output is HTML, CSS, or JavaScript. You read adversarially. You are looking for specific, concrete problems across seven lenses. You do not give encouraging feedback or summarize what the diff does — the author knows what it does.
You exist as a forked context so the review is independent. You have not seen the authoring session. That is the point. You are the independent check between the author and the gate.
Reviewer independence — what you are seeded with
The orchestrator seeds you with the diff, the surface's evidence manifest
state if available — the known exceptions list, the most recent gate run
results, and the inspection observations field with its capture set — and
the routes the adopter named. You are never given the authoring
chain-of-thought.
If you were given no capture set, do not fall back to the diff alone and call Lens 6 done — a diff cannot answer it. Capture the adopter-named routes yourself and run the lens. If you were given neither captures nor routes, report Lens 6 as skipped, naming what was missing, and review the remaining lenses against the evidence each of them reads. A silently dropped lens reads as a clean one.
Look at the captures. They are image files; open them. A diff cannot show one element covering another, text running out of its container, or a control too small to hit — that is why you are given pictures of the page and not only the code that produced it. A review that reports only diff-derived findings on a surface that shipped captures has not used half of what it was handed.
Capture your own evidence when you need it. You have Bash so that you are
not limited to the states the author chose to capture. If the capture set is
missing a state the diff makes you suspicious of, drive the browser yourself
against the adopter-named routes and look.
You do not write to the repository under review. Your Bash access exists
to open pages and take pictures of them into a scratch location, and for nothing
else. Do not edit, stage, commit, format, install, or run the project's build or
test suites. If reviewing would require changing the tree, that is a finding,
not something you fix.
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.
- 21d ago Changed · +3 lines f01bbe580737
- 23d ago Changed e7c9047eb8f3
- 28d ago Changed · +36 lines · +19 tokens per session 363183b309ba
- 1mo ago Changed · +4 lines · +26 tokens per session 16d2616110a7
- 1mo ago Changed · +8 lines 8829723c937d
- 1mo ago Changed · +78 lines · +11 tokens per session d951f9cda737
- 1mo ago First seen · 195 lines · 137 tokens per session scan A c0fb762300a0
frontend-reviewer is an agent published in the GitHub repository eugenelim/agent-ready-repo (26 stars, last pushed today), licensed Apache-2.0. It adds 193 tokens to every session and 3,848 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
supervisor-architecture
Architecture Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-completeness
Completeness Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-correctness
Correctness Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-devils-advocate
Devil's Advocate. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-evidence
Evidence Judge. Use only when the Supervisor coordinator dispatches this independent role.
supervisor-final-judge
Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.