review-stack-audit

A recurring check of whether paid AI code-review tools still provide enough value for their cost. It examines billing status, usage limits, throughput, and each tool’s distinct contribution.

In plain words
What is it for?
Use it to audit a review-tool stack and produce an advisory report or GitHub issues; it does not change subscriptions or repository rules.
Why use it?
It can reveal expired subscriptions, reduced limits, unnecessary spending, or review bottlenecks before they disrupt development.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/auerbachb/claude-code-config/review-stack-audit
Any agent
npx skills add auerbachb/claude-code-config --skill review-stack-audit
Clone the repo
git clone --depth 1 https://github.com/auerbachb/claude-code-config

Made for: Claude Code, Codex.

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,207 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00090 $0.04207
Opus 5 $0.00045 $0.02103
Sonnet 5 $0.00018 $0.00841
Haiku 4.5 $0.00009 $0.00421

Measured 2d ago against content hash a71ffddecc36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-stack-audit 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (drift.sh, measure.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/review-stack-audit/SKILL.md · 385 lines

How it starts

The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.

review-stack-audit — do the review tools still earn their keep?

Issue #1199 realigned the review chain with what we actually pay for. That was a snapshot. Subscriptions lapse, caps shrink without notice, pricing moves, and new tools appear — and none of it announces itself. The last two mismatches (BugBot's spend cap, CodeAnt's "not subscribed" state) both surfaced as a bad afternoon of PRs queuing on review rather than as a line item anyone caught early.

This skill is the recurring version of that check.

ADVISORY ONLY — NON-NEGOTIABLE. This skill never edits a rule, skill, script, or config, and never changes a subscription. Not when the verdict is obvious. Its entire output surface is a snapshot, a report, and GitHub issues. A human lands any change through the normal issue → branch → PR flow. Billing actions are the user's alone — this skill says "this looks like a bill with no return", never "cancelled it for you".

Sibling to /harness-audit, not part of it. That audit asks whether the harness already does natively what we automate by hand — an internal-redundancy axis. This one asks whether external spend still buys value. Same cadence, same advisory posture, same issue-filing discipline; different question.

Resolve the repository locator before either engine runs:

resolve_script() {
  local name="$1" candidate
  for candidate in \
    "$HOME/.claude/skills-worktree/.claude/scripts/$name" \
    "$HOME/.claude/scripts/$name" \
    ".claude/scripts/$name"; do
    if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
  done
  return 1
}
REPO_ROOT_SH=$(resolve_script repo-root.sh || true)
[[ -n "$REPO_ROOT_SH" ]] || { echo "ERROR: repo-root.sh not found (checked all three paths) — review-stack audit root unavailable" >&2; exit 1; }

The two engines

Both are plain scripts, so the judgment in this file stays small and their behavior is testable offline (.claude/scripts/tests/review-stack-audit.test.sh).

Engine Job
measure.sh What each tool actually did: billed signals, caps, throughput, unique value. No verdicts.
drift.sh Snapshot vs baseline → one finding per divergence, each with a stable dedup marker. Pure function of two JSON files.

Read the full file on GitHub · 385 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 385 lines · 90 tokens per session scan A a71ffddecc36

Subscribe to this mod's changes

review-stack-audit is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 3d ago), licensed MIT. It adds 90 tokens to every session and 4,207 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 2026-08-31.