shallow

A shortened code-review command for a quick review using built-in bug finders, an auditor, and a verifier.

In plain words
What is it for?
Use it for focused bug fixes, cross-repository checks, or when you mainly want obvious bugs found quickly.
Why use it?
It provides a predictable, lighter review by skipping deeper signal analysis and domain-specific critics.

Command

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 commands/closedloop-ai/claude-plugins/shallow
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 597 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 $0.00028 $0.00597
Opus 5 $0.00014 $0.00298
Sonnet 5 $0.00006 $0.00119
Haiku 4.5 $0.00003 $0.00060

Measured 2d ago against content hash c2e65a3a1991, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shallow 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.

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.

plugins/code-review/commands/shallow.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shallow Code Review (PLN-807)

This command is shorthand for /start --depth shallow. Follow every instruction in ${CLAUDE_PLUGIN_ROOT}/commands/start.md verbatim, with one binding:

DEPTH = "shallow" for the entire run. Pass --depth shallow to every helper that accepts the flag (notably prepare-run, hygiene, review-state-read, and review-state-write).

What shallow does

Component shallow standard deep
Hygiene (deterministic)
signal_extraction
coverage_critic
bug_hunter_a (partitioned at >5000 LOC)
bug_hunter_b
unified_auditor
critic-gates.json domain critics ✓ (≤3) ✓ (≤5)
Verifier
fast_path_reviewer (auto on tiny PRs) ✓ (auto) ✓ (auto) ✓ (auto)

When to use

  • Quick sanity check on a focused bugfix.
  • Cross-repo CI where you want predictable behavior regardless of critic-gates.json shape.
  • "Just find the obvious bugs" — bug-finding fleet intact; opinion-layer agents skipped.

When NOT to use

If the PR is > 3000 LOC, touches schema/migrations, or modifies public API surfaces (plugin.json, index.ts, init.py), shallow will emit a tier_mismatch_nudge MEDIUM finding (category Coverage) suggesting --depth standard. Pay attention to that nudge — those are the cases shallow's missing reviewers commonly catch.

Execution

Follow start.md from "0a. Resolve plugin root" through every gate and stage, with DEPTH = "shallow" substituted into every helper invocation. The run plan emitted by prepare-run --depth shallow includes the core pipeline minus 10 standard-only stages (signal extraction, coverage planning/critic, budget arbitrate, derive/verify spawn-spec). The walker behavior is otherwise unchanged. stage_19c_derive_static_spec runs in place of stage_19b_derive_spawn_spec and produces an arbitrate_status: "static" spec with BHA × N + BHB + unified_auditor.

Read the full file on GitHub · 39 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. 2d ago First seen · 39 lines · 28 tokens per session scan A c2e65a3a1991

Subscribe to this mod's changes

shallow is a command published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 28 tokens to every session and 597 once invoked, about $0.0001 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.