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/saeedkolivand/ai-job-hunter-appWrote 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/commands/saeedkolivand/ai-job-hunter-app/review-stats)<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.
<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>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 | $0.00046 | $0.00760 |
| Opus 5 | $0.00023 | $0.00380 |
| Sonnet 5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
review-stats scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report the review system's own performance — the eval loop that tells us whether the hardening program is working. All data is local JSONL; compute with node -e one-liners (both files may be absent on a fresh clone — degrade gracefully, report "no data yet").
1. Gate + pre-push metrics (.claude/.review-metrics.jsonl)
Per kind (stop-gate, pre-push, …) over the window ($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 jsonwrapper 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-pushREVIEW_SKIP) — a rising trend means the gate is becoming theater; investigate why - mean
duration_msper 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.
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.
- 13d ago First seen · 34 lines · 46 tokens per session scan A 886dec6ab2cb
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.
Other commands, from other repositories
quiz-result
Analyze quiz progress over time and the weak areas to study next, from a KMS scores log.
devkit.react.code-review
Provides comprehensive React 19 + Tailwind CSS code review focusing on modern patterns, hooks, Server Components, Actions, performance, accessibility, and Tailwind best practices. Use when reviewing React code changes or before merging pull requests.
codebase-review
Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.
cargo-clippy
Command "cargo-clippy" from olorehq/olore, covering cargo-clippy(1), name, description and see also.
rust-critique
Deep code critique — read the target Rust code and apply the full review process. Evaluates soundness, ownership, error handling, type design, async correctness, performance, and architecture. Think like a senior Rust engineer giving honest feedback.
rust-review
Rust code review for ownership, safety, and idiomatic patterns.