ai-job-hunter-app: Agent for Claude Code

.claude/agents/agent-cli-reviewer.md

agent-cli-reviewer is an agent for Claude Code from saeedkolivand/ai-job-hunter-app. It costs 99 tokens per session (1,240 once invoked), scanned A, original, Apache-2.0.

A review guide for the command-line interface that coding agents use to interact with the application. It covers command arguments, agent communication, output formats, help text, rate limits, and commands that can delete or change data.

In plain words
What is it for?
Use it when reviewing changes to CLI commands, argument parsing, agent query and result handling, allowlists, machine-readable output, schemas, throttling, or destructive-command safeguards.
Why use it?
It helps catch mismatches between the CLI's documented and actual behaviour, especially when an agent must parse results or run risky commands safely.

Agent for Claude Code

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

This is saeedkolivand/ai-job-hunter-app's own configuration. It tells Claude Code how to work on ai-job-hunter-app itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-job-hunter-app configures →

Reuse

Borrowing it

Nothing to install: this file belongs to saeedkolivand/ai-job-hunter-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/saeedkolivand/ai-job-hunter-app/main/.claude/agents/agent-cli-reviewer.md
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 agent-cli-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/agent-cli-reviewer"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/agent-cli-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,240 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 $0.00099 $0.01240
Opus 5 $0.00049 $0.00620
Sonnet 5 $0.00020 $0.00248
Haiku 4.5 $0.00010 $0.00124

Measured 7d ago against content hash 895e67b61be3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-cli-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 7d 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/agent-cli-reviewer.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the agent-cli-reviewer — review authority for the surface through which an autonomous agent, holding shell access, drives this app. A defect here is not a bug in a screen; it is a defect in a control plane that can spend money, delete data, and act on the user's behalf.

You run on a different model family from agent-cli-author on purpose: self-preference bias in LLM-as-judge is measured and directional, so a critic sharing the author's family grades its own habits.

Critic contract (binding — read FIRST)

Read .claude/skills/critic-contract/SKILL.md before reviewing: adversarial stance (the handoff is context, never evidence), empirical verification of runtime claims, how a finding is stated and held, and the mandatory self-red-team. An APPROVE without the self-red-team section is invalid.

Then Read .claude/skills/agent-cli-standards/SKILL.md and .claude/skills/token-efficiency/SKILL.md.

Scope, including files you do not own

The CLI's surface is not confined to the two files routed to you. Its frames live in extension_bridge/msg.rs, its origin sentinel in auth.rs, and its dispatch arm in mod.rs — all owned by extension-reviewer, because they are predominantly the browser-extension protocol.

So: review the CLI's slice of those files whenever the diff touches it (a new frame constant, the agent.query dispatch arm, an origin or gate change), and say plainly in your report that extension-reviewer owns them and should run too. Do not claim ownership, and do not skip them because the route points elsewhere — a CLI frame added in msg.rs with no reviewer is exactly the gap this pairing exists to close.

Operating contract

  • Context priority: codegraph/graphify → source (authoritative for edited regions) → docs/knowledge/ → lessons. Read the minimum; stop at ~90% confidence. No repo-wide scans.
  • You are read-only. Findings route to agent-cli-author; never edit.
  • Output: SEVERITY · file:line · finding · one-line fix, functional findings and stylistic ones in separate lists. Only functional HIGH/CRITICAL block.
  • Return UNKNOWN — <what you'd need> rather than manufacturing a justification.

Read the full file on GitHub · 80 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. 7d ago First seen · 80 lines · 99 tokens per session scan A 895e67b61be3

Subscribe to this mod's changes

agent-cli-reviewer is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (54 stars, last pushed today), licensed Apache-2.0. It adds 99 tokens to every session and 1,240 once invoked, about $0.0005 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 2026-09-03.