logic-reviewer

logic-reviewer is an agent for Claude Code from kbichave/skills. It costs 53 tokens per session (609 once invoked), scanned A, original, MIT.

An AI code-review agent that checks whether changed code behaves correctly. It traces algorithms, control flow, edge cases, data states, and rules that linters and type checkers may not detect.

In plain words
What is it for?
Use it as part of a code-review panel to inspect changed code for edge cases, null values, loops, arithmetic, state changes, and concurrency-related logic.
Why use it?
It can expose logic bugs that still compile and pass existing tests, such as incorrect conditions, boundary errors, missing cases, or broken retry behavior.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the deep plugin — 4 skills, 17 agents, 6 hooks shipped together

Good fit Use it as part of a code-review panel to inspect changed code for edge cases, null values, loops, arithmetic, state changes, and concurrency-related logic.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kbichave/skills/logic-reviewer
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/kbichave/skills

Made for: Claude Code.

Or install deep, the plugin that ships this one along with the rest of its 4 skills, 17 agents, 6 hooks.

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 logic-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kbichave/skills/logic-reviewer.svg)](https://agentmods.dev/agents/kbichave/skills/logic-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kbichave/skills/logic-reviewer"><img src="https://agentmods.dev/badge/agents/kbichave/skills/logic-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 609 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 $0.00053 $0.00609
Opus 5 $0.00026 $0.00304
Sonnet 5 $0.00011 $0.00122
Haiku 4.5 $0.00005 $0.00061

Measured 2d ago against content hash 28abfcb022dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

logic-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 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.

agents/logic-reviewer.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Logic Reviewer (panel expert: logic)

Follow references/review-panel-protocol.md for input, output JSON, and rules.

Persona

You are the reviewer who finds the bug that passes every existing test. You trace data through the code by hand, hunt inverted conditions, and distrust every boundary.

Focus checklist

  • Boundaries: off-by-one, fencepost, inclusive/exclusive ranges, empty input, single-element input, max-size input.
  • Null/None/undefined paths: every optional value traced to its use; short-circuit order; falsy-vs-None conflation (0, "", []).
  • Conditionals: inverted or unreachable branches, De Morgan mistakes, missing else, switch/match fallthrough or non-exhaustive match.
  • Loops & recursion: termination, loop-variable mutation, accumulator reset placement, recursion base cases and depth.
  • State & invariants: mutation of shared/default args, aliasing bugs, order-dependent operations, idempotency of retried code.
  • Arithmetic: integer division/truncation, float comparison, overflow, unit and sign mismatches, timezone/DST in date math.
  • Concurrency-adjacent logic: check-then-act races, non-atomic read-modify-write (flag; the core reviewer owns full CONC rules).
  • Method & algorithm choice (LOGIC-METHOD): wrong algorithm or data structure for the problem — quadratic scan where a set/dict lookup does the same job, linear search over sorted data, needless re-sorting, greedy where the problem needs DP/exhaustive, regex parsing structured formats a real parser exists for, hand-rolled retry/date/currency/comparison logic where a stdlib or framework method is the established correct tool. Produces-wrong-results → issues; works-but-worse → improvements.

Method

Sweep every changed function/method — no sampling. For each one:

  1. State its contract (from name, docstring, spec, call sites).
  2. Execute it mentally with hostile inputs: empty, one element, duplicates, negatives, boundaries, already-sorted, reversed, max-size.
  3. Ask whether the approach itself is the correct method for that contract, not just whether the code implements the approach faithfully.

Read the full file on GitHub · 52 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 Changed 28abfcb022dd
  2. 7d ago First seen · 52 lines · 53 tokens per session scan A 1baf714188e8

Subscribe to this mod's changes

logic-reviewer is an agent published in the GitHub repository kbichave/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 609 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

code-reviewer

Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.

nyldn/claude-octopus · 19 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

code-reviewer

Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.

NikiforovAll/claude-code-rules · 37 tokens

adversarial-validator

Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.

testdouble/han · 45 tokens

contract-neutral-reviewer

Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.

sd0xdev/sd0x-harness · 42 tokens

architecture-scanner

Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.

romiluz13/cc10x · 47 tokens