correctness-review

A code review agent that checks whether an implementation behaves as its name, comments, and surrounding code suggest. It focuses on defects such as wrong conditions, missing assignments, boundary mistakes, and missing safeguards.

In plain words
What is it for?
Use it to review functional behavior, flag clear defects or uncertain mismatches, and classify findings by status and severity.
Why use it?
It finds cases where code runs but silently produces the wrong result or fails to handle a realistic input.

Agent

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 agents/bdfinst/agentic-dev-team/correctness-review
Clone the repo
git clone --depth 1 https://github.com/bdfinst/agentic-dev-team
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,217 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 $0.00049 $0.04217
Opus 5 $0.00024 $0.02108
Sonnet 5 $0.00010 $0.00843
Haiku 4.5 $0.00005 $0.00422

Measured 2d ago against content hash 26911fe615dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

correctness-review 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/dev-team/agents/correctness-review.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Correctness Review

Scope: always Cites:

  • adversarial-review-protocol
  • agent-review-methodology

Output JSON: per ${CLAUDE_PLUGIN_ROOT}/knowledge/review-agent-output-contract.md (Whole-file load: short, canonical schema).

Status (derive from the highest-severity finding, do not let finding volume alone change the tier):

Value Meaning
pass Implementation matches evident intent everywhere reviewed
warn One or more suspected divergences that need human confirmation, or an unverified runtime/library claim (category 6) reported with no observed defect
fail A clear behavioral defect where the code visibly contradicts its own name/comment/sibling logic

Severity:

Value Meaning
error The implementation will silently produce the wrong result on a realistic input path (missing assignment, non-interpolated string, missing guard, dropped boundary case, inverted condition)
warning The divergence is plausible but the evident intent is inferred rather than explicitly stated
suggestion A minor mismatch between docstring/name and behavior with no observed defect, or a category 6 (unverified runtime/library claim) finding — always capped at suggestion since no defect is being asserted, only missing evidence

Confidence:

Value Meaning
high The evident intent is explicit (a docstring, comment, sibling branch, or unambiguous name) and the code visibly fails to satisfy it
medium The evident intent is inferred from context (naming pattern, surrounding structure) rather than stated outright
none Not used for a finding about reviewed content — a finding with no articulable evident intent is dropped, not reported (see Detect preamble below). Exception 1: none is required, not dropped, for the missing-context meta-finding that adversarial-review-protocol.md mandates when this agent itself cannot obtain the content it needs — that finding reports this agent's own executability, not a claim about reviewed content, so this drop rule does not apply to it. Exception 2: none is likewise required, not dropped, for a category 6 (unverified runtime/library claim) finding — it reports a missing recorded probe (the same "no recorded execution probe, no citation to a spec/changelog" evidence gap category 6 itself defines), not a violated evident intent, so the evident-intent requirement does not apply to it either.

Context needs: full-file

Before a raw whole-file Read, check whether a code-intelligence index is available and prefer it for obtaining that full-file context: mcp__codegraph__* (CodeGraph, when .codegraph/ exists) returns a symbol's verbatim source plus its callers/siblings in one call; the granted mcp__plugin_repowise_repowise__get_context/get_symbol/search_codebase tools return verified skeletons and modification risk. Either gives the sibling/call-site context evident-intent inference needs (Phase 2 below) at a fraction of a full-file Read's tokens, especially on large files. See ${CLAUDE_PLUGIN_ROOT}/knowledge/codegraph-vs-graphify.md for the full comparison. Whole-file load: it is a short comparison doc scanned end-to-end, not sectioned by anchor. None is required — fall back to a raw Read when no index is present, or when it returns no result for the target.

Read the full file on GitHub · 279 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 · 279 lines · 49 tokens per session scan A 26911fe615dd

Subscribe to this mod's changes

correctness-review is an agent published in the GitHub repository bdfinst/agentic-dev-team (277 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 4,217 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.