review-stats

review-stats is a command for Claude Code from saeedkolivand/ai-job-hunter-app. It costs 46 tokens per session (760 once invoked), scanned A, original, Apache-2.0.

A command for producing a health report from review-system log files.

In plain words
What is it for?
Use it to report findings per run, blocking and parsing failures, fallback and suppression rates, resolved findings, and missed issues attributed to CodeRabbit.
Why use it?
It makes review quality and failure patterns visible instead of requiring someone to inspect the logs manually.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to report findings per run, blocking and parsing failures, fallback and suppression rates, resolved findings, and missed issues attributed to CodeRabbit.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/saeedkolivand/ai-job-hunter-app/review-stats
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 review-stats

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/saeedkolivand/ai-job-hunter-app/review-stats"><img src="https://agentmods.dev/badge/commands/saeedkolivand/ai-job-hunter-app/review-stats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 760 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 $0.00046 $0.00760
Opus 5 $0.00023 $0.00380
Sonnet 5 $0.00009 $0.00152
Haiku 4.5 $0.00005 $0.00076

Measured 13d ago against content hash 886dec6ab2cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-stats 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 13d 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/commands/review-stats.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Report the review system's own performance — the eval loop that tells us whether the hardening program is working. All data is local JSONL; compute with node -e one-liners (both files may be absent on a fresh clone — degrade gracefully, report "no data yet").

1. Gate + pre-push metrics (.claude/.review-metrics.jsonl)

Per kind (stop-gate, pre-push, …) over the window ($ARGUMENTS days, default 30):

  • runs, and outcome distribution (clean / advisory / blocked / tier0-block / reemit-block / reemit-advisory / cache-skip / degraded / llm-unavailable / parse-failed / error)
  • findings per run by severity (mean), block rate
  • parse-failure rate (parse_failed) — >5% means the schema-1 contract is drifting; consider --output-format json wrapper parsing
  • sg_fallback rate — nonzero means ast-grep is missing/broken locally
  • cache-skip + re-emit counts (reemits) — how much work the ledger/caches are saving
  • suppressed counts (suppressed) — convergence + category suppression volume
  • audited skips (skipped: true, pre-push REVIEW_SKIP) — a rising trend means the gate is becoming theater; investigate why
  • mean duration_ms per outcome

2. Ledger analysis (.claude/.review-ledger.jsonl)

  • open vs resolved-changed vs suppressed, by category
  • ignore streaks: open entries with reemits ≥ 2 — candidates approaching category auto-suppression (only style/perf/i18n can suppress; anything else with a streak is a real unresolved problem — surface it)
  • resolution rate: resolved-changed ÷ (open + resolved-changed) per category — low resolution in a category = findings devs don't act on = calibrate that category's rules/prompts

3. CodeRabbit miss rate (best-effort, needs gh auth + network)

For merged PRs in the window (gh pr list --state merged), fetch review comments authored by coderabbitai (gh api repos/{owner}/{repo}/pulls/<n>/comments). A CodeRabbit finding on a file for which our metrics/ledger recorded NO finding in that PR's branch = a miss — the number this whole program exists to drive down. Report: misses, total CodeRabbit findings, miss rate, and the missed findings themselves (file + first line of the comment) so they can become checklist rules or ast-grep rules. Note the coverage caveat: CodeRabbit is on-demand, so only PRs where it was triggered contribute.

Read the full file on GitHub · 34 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. 13d ago First seen · 34 lines · 46 tokens per session scan A 886dec6ab2cb

Subscribe to this mod's changes

review-stats is a command published in the GitHub repository saeedkolivand/ai-job-hunter-app (55 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 760 once invoked, about $0.0002 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.