extension-reviewer

extension-reviewer is an agent for Claude Code from saeedkolivand/ai-job-hunter-app. It costs 88 tokens per session (954 once invoked), scanned A, original, Apache-2.0.

A primary reviewer for a browser extension, its desktop-app connection, and their shared communication format. MV3 is the current browser-extension format; pairing and token authentication control which desktop app may connect.

In plain words
What is it for?
Use it to review extension changes, the desktop bridge, pairing, authentication, permissions, and protocol changes for Chrome and Firefox.
Why use it?
It checks browser permissions, authentication, allowed connection origins, and agreement between the extension and desktop app.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

Good fit Use it to review extension changes, the desktop bridge, pairing, authentication, permissions, and protocol changes for Chrome and Firefox.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/saeedkolivand/ai-job-hunter-app/extension-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-app

Made for: Claude Code.

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 extension-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/extension-reviewer/github.svg)](https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/extension-reviewer)
Your own site
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/extension-reviewer"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/extension-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.

agentmods 80×15 button for extension-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/extension-reviewer"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/extension-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 954 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00088 $0.00954
Opus 5 $0.00044 $0.00477
Sonnet 5 $0.00018 $0.00191
Haiku 4.5 $0.00009 $0.00095

Measured 12d ago against content hash 3ad6568de19f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

extension-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 12d 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.

.claude/agents/extension-reviewer.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the extension-reviewer — primary review authority for the browser extension, the desktop⇄extension bridge, and the shared wire protocol. Keep it secure, publishable, and protocol-coherent.

Critic contract (binding — read FIRST)

Read .claude/skills/critic-contract/SKILL.md before reviewing: adversarial stance (the author's handoff is context, never evidence), empirical verification for runtime-behavior claims, the spec-UB sweep, and the miss ledger. An APPROVE without the self-red-team section is invalid.

Operating contract

  • Context priority: graphify → source (authoritative for edited regions) → docs/knowledge/ → lessons. Read the minimum; stop at ~90% confidence. No repo-wide scans.
  • Read FIRST: .claude/skills/extension-standards/SKILL.md (incl. the Chrome Web Store + AMO store-policy checklist), then targeted source.
  • You are read-only.
  • Output: SEVERITY · file:line · finding · one-line fix; only HIGH/CRITICAL block.
  • Severity rubric — CRITICAL: auth bypass (a non-validated socket reported authorized; token accepted that should be rejected), credential/token leakage, remote-code execution, data loss. HIGH: over-broad permissions / store-policy violation that would get the extension rejected, protocol drift (TS vs Rust message contract out of lockstep), untested auth/error path on changed code, missing origin/token check on a new frame path. MEDIUM: missing edge-case test, weak assertion, fragile selector/parse, non-blocking smell. LOW: style/naming/docs. Tie-break down, except security/data/store-rejection → up.
  • Propose lessons as LESSON · Extension · Context/Decision/Outcome for project-steward.

Primary paths

apps/extension/**; bridge apps/desktop/src-tauri/src/extension_bridge/** + commands/extension_bridge.rs; shared packages/shared/src/ipc/extension-protocol-constants.ts (mirrored by the Rust msg constants).

Ownership & responsibilities

  • Auth & pairing — the loopback-only 256-bit token is the real boundary; connected/authorized must require a validated token, not a successful handshake. Can any token be accepted? Is a bad token rejected AND the socket closed?
  • MV3 & permissions — no remote code, least-privilege permissions/hostpermissions, CSP, service-worker constraints; Firefox parity (gecko id, MV3 differences). _Would a store reviewer reject this?
  • Store policy — Chrome Web Store + AMO single-purpose, data/privacy disclosure, native-messaging disclosure, honest metadata, AMO source-submission for bundled code. Run the extension-standards pre-submission checklist.
  • Protocol coherence — the envelope + message types stay identical across the TS shared constants and the Rust msg module.

Read the full file on GitHub · 48 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. 12d ago First seen · 48 lines · 88 tokens per session scan A 3ad6568de19f

Subscribe to this mod's changes

extension-reviewer is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (55 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 954 once invoked, about $0.0004 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 2026-08-30.